mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-16 02:45:13 +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.
175 lines
No EOL
6.3 KiB
Python
175 lines
No EOL
6.3 KiB
Python
"""
|
|
Structured Query Service - orchestrates natural language question processing.
|
|
Takes a question, converts it to GraphQL via nlp-query, executes via rows-query,
|
|
and returns the results.
|
|
"""
|
|
|
|
import json
|
|
import logging
|
|
from typing import Dict, Any, Optional
|
|
|
|
from ...schema import StructuredQueryRequest, StructuredQueryResponse
|
|
from ...schema import QuestionToStructuredQueryRequest, QuestionToStructuredQueryResponse
|
|
from ...schema import RowsQueryRequest, RowsQueryResponse
|
|
from ...schema import Error
|
|
|
|
from ...base import FlowProcessor, ConsumerSpec, ProducerSpec, RequestResponseSpec
|
|
|
|
# Module logger
|
|
logger = logging.getLogger(__name__)
|
|
|
|
default_ident = "structured-query"
|
|
|
|
class Processor(FlowProcessor):
|
|
|
|
def __init__(self, **params):
|
|
|
|
id = params.get("id", default_ident)
|
|
|
|
super(Processor, self).__init__(
|
|
**params | {
|
|
"id": id,
|
|
}
|
|
)
|
|
|
|
self.register_specification(
|
|
ConsumerSpec(
|
|
name = "request",
|
|
schema = StructuredQueryRequest,
|
|
handler = self.on_message
|
|
)
|
|
)
|
|
|
|
self.register_specification(
|
|
ProducerSpec(
|
|
name = "response",
|
|
schema = StructuredQueryResponse,
|
|
)
|
|
)
|
|
|
|
# Client spec for calling NLP query service
|
|
self.register_specification(
|
|
RequestResponseSpec(
|
|
request_name = "nlp-query-request",
|
|
response_name = "nlp-query-response",
|
|
request_schema = QuestionToStructuredQueryRequest,
|
|
response_schema = QuestionToStructuredQueryResponse
|
|
)
|
|
)
|
|
|
|
# Client spec for calling rows query service
|
|
self.register_specification(
|
|
RequestResponseSpec(
|
|
request_name = "rows-query-request",
|
|
response_name = "rows-query-response",
|
|
request_schema = RowsQueryRequest,
|
|
response_schema = RowsQueryResponse
|
|
)
|
|
)
|
|
|
|
logger.info("Structured Query service initialized")
|
|
|
|
async def on_message(self, msg, consumer, flow):
|
|
"""Handle incoming structured query request"""
|
|
|
|
try:
|
|
request = msg.value()
|
|
|
|
# Sender-produced ID
|
|
id = msg.properties()["id"]
|
|
|
|
logger.info(f"Handling structured query request {id}: {request.question[:100]}...")
|
|
|
|
# Step 1: Convert question to GraphQL using NLP query service
|
|
logger.info("Step 1: Converting question to GraphQL")
|
|
nlp_request = QuestionToStructuredQueryRequest(
|
|
question=request.question,
|
|
max_results=100 # Default limit
|
|
)
|
|
|
|
nlp_response = await flow("nlp-query-request").request(nlp_request)
|
|
|
|
if nlp_response.error is not None:
|
|
raise Exception(f"NLP query service error: {nlp_response.error.message}")
|
|
|
|
if not nlp_response.graphql_query:
|
|
raise Exception("NLP query service returned empty GraphQL query")
|
|
|
|
logger.info(f"Generated GraphQL query: {nlp_response.graphql_query[:200]}...")
|
|
logger.info(f"Detected schemas: {nlp_response.detected_schemas}")
|
|
logger.info(f"Confidence: {nlp_response.confidence}")
|
|
|
|
# Step 2: Execute GraphQL query using objects query service
|
|
logger.info("Step 2: Executing GraphQL query")
|
|
|
|
# Convert variables to strings (GraphQL variables can be various types, but Pulsar schema expects strings)
|
|
variables_as_strings = {}
|
|
if nlp_response.variables:
|
|
for key, value in nlp_response.variables.items():
|
|
if isinstance(value, str):
|
|
variables_as_strings[key] = value
|
|
else:
|
|
variables_as_strings[key] = str(value)
|
|
|
|
# Use collection from request. Workspace isolation is
|
|
# enforced by flow.workspace at the rows-query service.
|
|
objects_request = RowsQueryRequest(
|
|
collection=request.collection,
|
|
query=nlp_response.graphql_query,
|
|
variables=variables_as_strings,
|
|
operation_name=None
|
|
)
|
|
|
|
objects_response = await flow("rows-query-request").request(objects_request)
|
|
|
|
if objects_response.error is not None:
|
|
raise Exception(f"Rows query service error: {objects_response.error.message}")
|
|
|
|
# Handle GraphQL errors from the rows query service
|
|
graphql_errors = []
|
|
if objects_response.errors:
|
|
for gql_error in objects_response.errors:
|
|
graphql_errors.append(f"{gql_error.message} (path: {gql_error.path})")
|
|
|
|
logger.info("Step 3: Returning results")
|
|
|
|
# Create response
|
|
response = StructuredQueryResponse(
|
|
error=None,
|
|
data=objects_response.data or "null", # JSON string
|
|
errors=graphql_errors
|
|
)
|
|
|
|
logger.info("Sending structured query response...")
|
|
await flow("response").send(response, properties={"id": id})
|
|
|
|
logger.info("Structured query request completed")
|
|
|
|
except Exception as e:
|
|
|
|
logger.error(f"Exception in structured query service: {e}", exc_info=True)
|
|
|
|
logger.info("Sending error response...")
|
|
|
|
response = StructuredQueryResponse(
|
|
error = Error(
|
|
type = "structured-query-error",
|
|
message = str(e),
|
|
),
|
|
data = "null",
|
|
errors = []
|
|
)
|
|
|
|
await flow("response").send(response, properties={"id": id})
|
|
|
|
@staticmethod
|
|
def add_args(parser):
|
|
"""Add command-line arguments"""
|
|
|
|
FlowProcessor.add_args(parser)
|
|
|
|
# No additional arguments needed for this orchestrator service
|
|
|
|
def run():
|
|
"""Entry point for structured-query command"""
|
|
Processor.launch(default_ident, __doc__) |