mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-29 10:26:21 +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.
104 lines
2.7 KiB
Python
104 lines
2.7 KiB
Python
"""
|
|
Document embeddings query service. Input is vectors. Output is list of
|
|
embeddings.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from argparse import ArgumentParser
|
|
|
|
import logging
|
|
|
|
from .. schema import DocumentEmbeddingsRequest, DocumentEmbeddingsResponse
|
|
from .. schema import Error, Term
|
|
|
|
from . flow_processor import FlowProcessor
|
|
from . consumer_spec import ConsumerSpec
|
|
from . producer_spec import ProducerSpec
|
|
|
|
# Module logger
|
|
logger = logging.getLogger(__name__)
|
|
|
|
default_ident = "doc-embeddings-query"
|
|
default_concurrency = 10
|
|
|
|
class DocumentEmbeddingsQueryService(FlowProcessor):
|
|
|
|
def __init__(self, **params):
|
|
|
|
id = params.get("id")
|
|
concurrency = params.get("concurrency", default_concurrency)
|
|
|
|
super(DocumentEmbeddingsQueryService, self).__init__(
|
|
**params | { "id": id }
|
|
)
|
|
|
|
self.register_specification(
|
|
ConsumerSpec(
|
|
name = "request",
|
|
schema = DocumentEmbeddingsRequest,
|
|
handler = self.on_message,
|
|
concurrency = concurrency,
|
|
)
|
|
)
|
|
|
|
self.register_specification(
|
|
ProducerSpec(
|
|
name = "response",
|
|
schema = DocumentEmbeddingsResponse,
|
|
)
|
|
)
|
|
|
|
async def on_message(self, msg, consumer, flow):
|
|
|
|
try:
|
|
|
|
request = msg.value()
|
|
|
|
# Sender-produced ID
|
|
id = msg.properties()["id"]
|
|
|
|
logger.debug(f"Handling document embeddings query request {id}...")
|
|
|
|
docs = await self.query_document_embeddings(
|
|
flow.workspace, request,
|
|
)
|
|
|
|
logger.debug("Sending document embeddings query response...")
|
|
r = DocumentEmbeddingsResponse(chunks=docs, error=None)
|
|
await flow("response").send(r, properties={"id": id})
|
|
|
|
logger.debug("Document embeddings query request completed")
|
|
|
|
except Exception as e:
|
|
|
|
logger.error(f"Exception in document embeddings query service: {e}", exc_info=True)
|
|
|
|
logger.info("Sending error response...")
|
|
|
|
r = DocumentEmbeddingsResponse(
|
|
error=Error(
|
|
type = "document-embeddings-query-error",
|
|
message = str(e),
|
|
),
|
|
chunks=[],
|
|
)
|
|
|
|
await flow("response").send(r, properties={"id": id})
|
|
|
|
@staticmethod
|
|
def add_args(parser: ArgumentParser) -> None:
|
|
|
|
FlowProcessor.add_args(parser)
|
|
|
|
parser.add_argument(
|
|
'-c', '--concurrency',
|
|
type=int,
|
|
default=default_concurrency,
|
|
help=f'Number of concurrent requests (default: {default_concurrency})'
|
|
)
|
|
|
|
def run() -> None:
|
|
|
|
Processor.launch(default_ident, __doc__)
|
|
|