dc4607daa4
## Summary - Add shared span attributes for tool error diagnostics, including developer-facing messages when present. - Wire those attributes through MCP server, worker RunTool, and HTTP CallTool spans while keeping default MCP response content public-only. - Cover no-leak response behavior, non-recording spans, outputless worker responses, and the shared attribute contract. ## Verification - `uv run ruff format ...` - `uv run ruff check ...` - `uv run pytest -W ignore libs/tests/arcade_mcp_server/test_debug_exposure_integration.py libs/tests/core/test_log_extras.py libs/tests/worker/test_worker_base.py` Made with [Cursor](https://cursor.com) <!-- CURSOR_SUMMARY --> --- > [!NOTE] > **Medium Risk** > Adds new telemetry attributes that propagate tool error messages (including optional developer_message) into active spans across MCP server and worker execution paths; risk is mainly around potential leakage of sensitive developer messages into tracing backends and changes to observability contracts. > > **Overview** > Adds a shared `arcade_core.log_extras.build_tool_error_span_attributes()` helper and wires it into tool error paths so the current OpenTelemetry span is annotated with stable `tool_error_*` attributes (including `developer_message` when present). > > MCP tool calls now record these span attributes on failure while keeping default MCP response content sanitized, and `arcade-serve` records the same attributes on both `RunTool` and HTTP `CallTool` spans (handling `output=None`). Versions and dependency constraints are bumped to consume the new core helper, with tests added/updated to lock the span-attribute contract and verify behavior for non-recording spans and no-leak responses. > > <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit 33a53991d72140a662152f508dc53e9b769b9f07. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup> <!-- /CURSOR_SUMMARY -->
111 lines
3.5 KiB
Python
111 lines
3.5 KiB
Python
from arcade_core.log_extras import build_tool_error_span_attributes
|
|
from arcade_core.schema import (
|
|
ToolCallRequest,
|
|
ToolCallResponse,
|
|
)
|
|
from opentelemetry import trace
|
|
|
|
from arcade_serve.core.common import (
|
|
CatalogResponse,
|
|
HealthCheckResponse,
|
|
RequestData,
|
|
Router,
|
|
Worker,
|
|
WorkerComponent,
|
|
)
|
|
|
|
|
|
class CatalogComponent(WorkerComponent):
|
|
def __init__(self, worker: Worker) -> None:
|
|
self.worker = worker
|
|
|
|
def register(self, router: Router) -> None:
|
|
"""
|
|
Register the catalog route with the router.
|
|
"""
|
|
router.add_route(
|
|
"tools",
|
|
self,
|
|
method="GET",
|
|
response_type=CatalogResponse,
|
|
operation_id="get_catalog",
|
|
description="Get the catalog of tools",
|
|
summary="Get the catalog of tools",
|
|
tags=["Arcade"],
|
|
)
|
|
|
|
async def __call__(self, request: RequestData) -> CatalogResponse:
|
|
"""
|
|
Handle the request to get the catalog.
|
|
"""
|
|
tracer = trace.get_tracer(__name__)
|
|
with tracer.start_as_current_span("Catalog"):
|
|
return self.worker.get_catalog()
|
|
|
|
|
|
class CallToolComponent(WorkerComponent):
|
|
def __init__(self, worker: Worker) -> None:
|
|
self.worker = worker
|
|
|
|
def register(self, router: Router) -> None:
|
|
"""
|
|
Register the call tool route with the router.
|
|
"""
|
|
router.add_route(
|
|
"tools/invoke",
|
|
self,
|
|
method="POST",
|
|
response_type=ToolCallResponse,
|
|
operation_id="call_tool",
|
|
description="Call a tool",
|
|
summary="Call a tool",
|
|
tags=["Arcade"],
|
|
)
|
|
|
|
async def __call__(self, request: RequestData) -> ToolCallResponse:
|
|
"""
|
|
Handle the request to call (invoke) a tool.
|
|
"""
|
|
tracer = trace.get_tracer(__name__)
|
|
with tracer.start_as_current_span("CallTool") as current_span:
|
|
call_tool_request_data = request.body_json
|
|
call_tool_request = ToolCallRequest.model_validate(call_tool_request_data)
|
|
|
|
current_span.set_attribute("tool_name", str(call_tool_request.tool.name))
|
|
current_span.set_attribute("toolkit_version", str(call_tool_request.tool.version))
|
|
current_span.set_attribute("toolkit_name", str(call_tool_request.tool.toolkit))
|
|
if hasattr(self.worker, "environment"):
|
|
current_span.set_attribute("environment", self.worker.environment)
|
|
|
|
response = await self.worker.call_tool(call_tool_request)
|
|
if response.output and response.output.error:
|
|
for key, value in build_tool_error_span_attributes(response.output.error).items():
|
|
current_span.set_attribute(key, value)
|
|
return response
|
|
|
|
|
|
class HealthCheckComponent(WorkerComponent):
|
|
def __init__(self, worker: Worker) -> None:
|
|
self.worker = worker
|
|
|
|
def register(self, router: Router) -> None:
|
|
"""
|
|
Register the health check route with the router.
|
|
"""
|
|
router.add_route(
|
|
"health",
|
|
self,
|
|
method="GET",
|
|
response_type=HealthCheckResponse,
|
|
operation_id="health_check",
|
|
description="Health check",
|
|
summary="Health check",
|
|
tags=["Arcade"],
|
|
require_auth=False,
|
|
)
|
|
|
|
async def __call__(self, request: RequestData) -> HealthCheckResponse:
|
|
"""
|
|
Handle the request to check the health of the worker.
|
|
"""
|
|
return self.worker.health_check()
|