trustgraph/trustgraph-base/trustgraph/base/tool_service.py
cybermaggedon d35473f7f7
feat: workspace-based multi-tenancy, replacing user as tenancy axis (#840)
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.
2026-04-21 23:23:01 +01:00

129 lines
3.4 KiB
Python

"""
Tool invocation base class
"""
from __future__ import annotations
from argparse import ArgumentParser
import json
import logging
from prometheus_client import Counter
from .. schema import ToolRequest, ToolResponse, Error
from .. exceptions import TooManyRequests
from .. base import FlowProcessor, ConsumerSpec, ProducerSpec
# Module logger
logger = logging.getLogger(__name__)
default_concurrency = 1
class ToolService(FlowProcessor):
def __init__(self, **params):
id = params.get("id")
concurrency = params.get("concurrency", 1)
super(ToolService, self).__init__(**params | {
"id": id,
"concurrency": concurrency,
})
self.register_specification(
ConsumerSpec(
name = "request",
schema = ToolRequest,
handler = self.on_request,
concurrency = concurrency,
)
)
self.register_specification(
ProducerSpec(
name = "response",
schema = ToolResponse
)
)
if not hasattr(__class__, "tool_invocation_metric"):
__class__.tool_invocation_metric = Counter(
'tool_invocation_count', 'Tool invocation count',
["id", "flow", "name"],
)
async def on_request(self, msg, consumer, flow):
try:
request = msg.value()
# Sender-produced ID
id = msg.properties()["id"]
response = await self.invoke_tool(
flow.workspace,
request.name,
json.loads(request.parameters) if request.parameters else {},
)
if isinstance(response, str):
await flow("response").send(
ToolResponse(
error=None,
text=response,
object=None,
),
properties={"id": id}
)
else:
await flow("response").send(
ToolResponse(
error=None,
text=None,
object=json.dumps(response),
),
properties={"id": id}
)
__class__.tool_invocation_metric.labels(
id = self.id, flow = flow.name, name = request.name,
).inc()
except TooManyRequests as e:
raise e
except Exception as e:
# Apart from rate limits, treat all exceptions as unrecoverable
logger.error(f"Exception in tool service: {e}", exc_info=True)
logger.info("Sending error response...")
await flow.producer["response"].send(
ToolResponse(
error=Error(
type = "tool-error",
message = str(e),
),
text=None,
object=None,
),
properties={"id": id}
)
@staticmethod
def add_args(parser: ArgumentParser) -> None:
parser.add_argument(
'-c', '--concurrency',
type=int,
default=default_concurrency,
help=f'Concurrent processing threads (default: {default_concurrency})'
)
FlowProcessor.add_args(parser)