mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-06-11 07:45:13 +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.
150 lines
4.3 KiB
Python
150 lines
4.3 KiB
Python
from __future__ import annotations
|
|
|
|
import uuid
|
|
import asyncio
|
|
import logging
|
|
from typing import Any
|
|
|
|
from . subscriber import Subscriber
|
|
from . producer import Producer
|
|
from . spec import Spec
|
|
from . metrics import ConsumerMetrics, ProducerMetrics, SubscriberMetrics
|
|
|
|
# Module logger
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class RequestResponse(Subscriber):
|
|
|
|
def __init__(
|
|
self, backend, subscription, consumer_name,
|
|
request_topic, request_schema,
|
|
request_metrics,
|
|
response_topic, response_schema,
|
|
response_metrics,
|
|
):
|
|
|
|
super(RequestResponse, self).__init__(
|
|
backend = backend,
|
|
subscription = subscription,
|
|
consumer_name = consumer_name,
|
|
topic = response_topic,
|
|
schema = response_schema,
|
|
metrics = response_metrics,
|
|
)
|
|
|
|
self.producer = Producer(
|
|
backend = backend,
|
|
topic = request_topic,
|
|
schema = request_schema,
|
|
metrics = request_metrics,
|
|
)
|
|
|
|
async def start(self):
|
|
await self.producer.start()
|
|
await super(RequestResponse, self).start()
|
|
|
|
async def stop(self):
|
|
await self.producer.stop()
|
|
await super(RequestResponse, self).stop()
|
|
|
|
async def request(self, req, timeout=300, recipient=None):
|
|
|
|
id = str(uuid.uuid4())
|
|
|
|
q = await self.subscribe(id)
|
|
|
|
try:
|
|
|
|
await self.producer.send(
|
|
req,
|
|
properties={"id": id}
|
|
)
|
|
|
|
except Exception as e:
|
|
|
|
logger.error(f"Exception sending request: {e}", exc_info=True)
|
|
raise e
|
|
|
|
|
|
try:
|
|
|
|
while True:
|
|
|
|
resp = await asyncio.wait_for(
|
|
q.get(),
|
|
timeout=timeout
|
|
)
|
|
|
|
if recipient is None:
|
|
|
|
# If no recipient handler, just return the first
|
|
# response we get
|
|
return resp
|
|
else:
|
|
|
|
# Recipient handler gets to decide when we're done b
|
|
# returning a boolean
|
|
fin = await recipient(resp)
|
|
|
|
# If done, return the last result otherwise loop round for
|
|
# next response
|
|
if fin:
|
|
return resp
|
|
else:
|
|
continue
|
|
|
|
except Exception as e:
|
|
|
|
logger.error(f"Exception processing response: {e}", exc_info=True)
|
|
raise e
|
|
|
|
finally:
|
|
|
|
await self.unsubscribe(id)
|
|
|
|
# This deals with the request/response case. The caller needs to
|
|
# use another service in request/response mode. Uses two topics:
|
|
# - we send on the request topic as a producer
|
|
# - we receive on the response topic as a subscriber
|
|
class RequestResponseSpec(Spec):
|
|
def __init__(
|
|
self, request_name, request_schema, response_name,
|
|
response_schema, impl=RequestResponse
|
|
):
|
|
self.request_name = request_name
|
|
self.request_schema = request_schema
|
|
self.response_name = response_name
|
|
self.response_schema = response_schema
|
|
self.impl = impl
|
|
|
|
def add(self, flow: Any, processor: Any, definition: dict[str, Any]) -> None:
|
|
|
|
request_metrics = ProducerMetrics(
|
|
processor = flow.id, flow = flow.name, name = self.request_name
|
|
)
|
|
|
|
response_metrics = SubscriberMetrics(
|
|
processor = flow.id, flow = flow.name, name = self.request_name
|
|
)
|
|
|
|
rr = self.impl(
|
|
backend = processor.pubsub,
|
|
|
|
# Make subscription names unique, so that all subscribers get
|
|
# to see all response messages
|
|
subscription = (
|
|
processor.id + "--" + flow.workspace + "--" +
|
|
flow.name + "--" + self.request_name + "--" +
|
|
str(uuid.uuid4())
|
|
),
|
|
consumer_name = flow.id,
|
|
request_topic = definition["topics"][self.request_name],
|
|
request_schema = self.request_schema,
|
|
request_metrics = request_metrics,
|
|
response_topic = definition["topics"][self.response_name],
|
|
response_schema = self.response_schema,
|
|
response_metrics = response_metrics,
|
|
)
|
|
|
|
flow.consumer[self.request_name] = rr
|
|
|