apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-25 08:26:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

feat: workspace-based multi-tenancy, replacing user as tenancy axis (#840)

Browse source 
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.
This commit is contained in:
cybermaggedon 2026-04-21 23:23:01 +01:00 • committed by GitHub
parent 9332089b3d
commit d35473f7f7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
377 changed files with 6868 additions and 5785 deletions
Download patch file Download diff file Expand all files Collapse all files

54
tests/unit/test_structured_data/test_row_embeddings_query.py
View file

@ -24,11 +24,10 @@ def _make_processor(qdrant_client=None):
return proc
def _make_request(vector=None, user="test-user", collection="test-col",
def _make_request(vector=None, collection="test-col",
schema_name="customers", limit=10, index_name=None):
return RowEmbeddingsRequest(
vector=vector or [0.1, 0.2, 0.3],
user=user,
collection=collection,
schema_name=schema_name,
limit=limit,
@ -36,6 +35,14 @@ def _make_request(vector=None, user="test-user", collection="test-col",
)
def _make_flow(workspace="test-workspace", pub=None):
"""Make a mock flow object that is callable and has .workspace."""
flow = MagicMock()
flow.return_value = pub if pub is not None else AsyncMock()
flow.workspace = workspace
return flow
def _make_search_point(index_name, index_value, text, score):
point = MagicMock()
point.payload = {
@ -85,34 +92,33 @@ class TestFindCollection:
def test_finds_matching_collection(self):
proc = _make_processor()
mock_coll = MagicMock()
mock_coll.name = "rows_test_user_test_col_customers_384"
mock_coll.name = "rows_test_workspace_test_col_customers_384"
mock_collections = MagicMock()
mock_collections.collections = [mock_coll]
proc.qdrant.get_collections.return_value = mock_collections
result = proc.find_collection("test-user", "test-col", "customers")
result = proc.find_collection("test-workspace", "test-col", "customers")
# Prefix: rows_test_user_test_col_customers_
assert result == "rows_test_user_test_col_customers_384"
assert result == "rows_test_workspace_test_col_customers_384"
def test_returns_none_when_no_match(self):
proc = _make_processor()
mock_coll = MagicMock()
mock_coll.name = "rows_other_user_other_col_schema_768"
mock_coll.name = "rows_other_workspace_other_col_schema_768"
mock_collections = MagicMock()
mock_collections.collections = [mock_coll]
proc.qdrant.get_collections.return_value = mock_collections
result = proc.find_collection("test-user", "test-col", "customers")
result = proc.find_collection("test-workspace", "test-col", "customers")
assert result is None
def test_returns_none_on_error(self):
proc = _make_processor()
proc.qdrant.get_collections.side_effect = Exception("connection error")
result = proc.find_collection("user", "col", "schema")
result = proc.find_collection("workspace", "col", "schema")
assert result is None
@ -127,7 +133,7 @@ class TestQueryRowEmbeddings:
proc = _make_processor()
request = _make_request(vector=[])
result = await proc.query_row_embeddings(request)
result = await proc.query_row_embeddings("test-workspace", request)
assert result == []
@pytest.mark.asyncio
@ -136,13 +142,13 @@ class TestQueryRowEmbeddings:
proc.find_collection = MagicMock(return_value=None)
request = _make_request()
result = await proc.query_row_embeddings(request)
result = await proc.query_row_embeddings("test-workspace", request)
assert result == []
@pytest.mark.asyncio
async def test_successful_query_returns_matches(self):
proc = _make_processor()
proc.find_collection = MagicMock(return_value="rows_u_c_s_384")
proc.find_collection = MagicMock(return_value="rows_w_c_s_384")
points = [
_make_search_point("name", ["Alice Smith"], "Alice Smith", 0.95),
@ -153,7 +159,7 @@ class TestQueryRowEmbeddings:
proc.qdrant.query_points.return_value = mock_result
request = _make_request()
result = await proc.query_row_embeddings(request)
result = await proc.query_row_embeddings("test-workspace", request)
assert len(result) == 2
assert isinstance(result[0], RowIndexMatch)
@ -166,14 +172,14 @@ class TestQueryRowEmbeddings:
async def test_index_name_filter_applied(self):
"""When index_name is specified, a Qdrant filter should be used."""
proc = _make_processor()
proc.find_collection = MagicMock(return_value="rows_u_c_s_384")
proc.find_collection = MagicMock(return_value="rows_w_c_s_384")
mock_result = MagicMock()
mock_result.points = []
proc.qdrant.query_points.return_value = mock_result
request = _make_request(index_name="address")
await proc.query_row_embeddings(request)
await proc.query_row_embeddings("test-workspace", request)
call_kwargs = proc.qdrant.query_points.call_args[1]
assert call_kwargs["query_filter"] is not None
@ -182,14 +188,14 @@ class TestQueryRowEmbeddings:
async def test_no_index_name_no_filter(self):
"""When index_name is empty, no filter should be applied."""
proc = _make_processor()
proc.find_collection = MagicMock(return_value="rows_u_c_s_384")
proc.find_collection = MagicMock(return_value="rows_w_c_s_384")
mock_result = MagicMock()
mock_result.points = []
proc.qdrant.query_points.return_value = mock_result
request = _make_request(index_name="")
await proc.query_row_embeddings(request)
await proc.query_row_embeddings("test-workspace", request)
call_kwargs = proc.qdrant.query_points.call_args[1]
assert call_kwargs["query_filter"] is None
@ -198,7 +204,7 @@ class TestQueryRowEmbeddings:
async def test_missing_payload_fields_default(self):
"""Points with missing payload fields should use defaults."""
proc = _make_processor()
proc.find_collection = MagicMock(return_value="rows_u_c_s_384")
proc.find_collection = MagicMock(return_value="rows_w_c_s_384")
point = MagicMock()
point.payload = {} # Empty payload
@ -209,7 +215,7 @@ class TestQueryRowEmbeddings:
proc.qdrant.query_points.return_value = mock_result
request = _make_request()
result = await proc.query_row_embeddings(request)
result = await proc.query_row_embeddings("test-workspace", request)
assert len(result) == 1
assert result[0].index_name == ""
@ -219,13 +225,13 @@ class TestQueryRowEmbeddings:
@pytest.mark.asyncio
async def test_qdrant_error_propagates(self):
proc = _make_processor()
proc.find_collection = MagicMock(return_value="rows_u_c_s_384")
proc.find_collection = MagicMock(return_value="rows_w_c_s_384")
proc.qdrant.query_points.side_effect = Exception("qdrant down")
request = _make_request()
with pytest.raises(Exception, match="qdrant down"):
await proc.query_row_embeddings(request)
await proc.query_row_embeddings("test-workspace", request)
# ---------------------------------------------------------------------------
@ -243,7 +249,7 @@ class TestOnMessage:
])
mock_pub = AsyncMock()
flow = lambda name: mock_pub
flow = _make_flow(pub=mock_pub)
msg = MagicMock()
msg.value.return_value = _make_request()
@ -264,7 +270,7 @@ class TestOnMessage:
)
mock_pub = AsyncMock()
flow = lambda name: mock_pub
flow = _make_flow(pub=mock_pub)
msg = MagicMock()
msg.value.return_value = _make_request()
@ -284,7 +290,7 @@ class TestOnMessage:
proc.query_row_embeddings = AsyncMock(return_value=[])
mock_pub = AsyncMock()
flow = lambda name: mock_pub
flow = _make_flow(pub=mock_pub)
msg = MagicMock()
msg.value.return_value = _make_request()