remove legacy tracing

llama_stack/core/library_client.py

@@ -48,12 +48,7 @@ from llama_stack.core.utils.config import redact_sensitive_fields
 from llama_stack.core.utils.context import preserve_contexts_async_generator
 from llama_stack.core.utils.exec import in_notebook
 from llama_stack.log import get_logger
-from llama_stack.providers.utils.telemetry.tracing import (
-    CURRENT_TRACE_CONTEXT,
-    end_trace,
-    setup_logger,
-    start_trace,
-)
+
 
 logger = get_logger(name=__name__, category="core")
 
@@ -206,8 +201,6 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
         super().__init__()
         # when using the library client, we should not log to console since many
         # of our logs are intended for server-side usage
-        current_sinks = os.environ.get("TELEMETRY_SINKS", "sqlite").split(",")
-        os.environ["TELEMETRY_SINKS"] = ",".join(sink for sink in current_sinks if sink != "console")
 
         if in_notebook():
             import nest_asyncio
@@ -293,8 +286,6 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
             raise _e
 
         assert self.impls is not None
-        if Api.telemetry in self.impls:
-            setup_logger(self.impls[Api.telemetry])
 
         if not os.environ.get("PYTEST_CURRENT_TEST"):
             console = Console()
@@ -384,13 +375,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
         body, field_names = self._handle_file_uploads(options, body)
 
         body = self._convert_body(path, options.method, body, exclude_params=set(field_names))
-
-        trace_path = webmethod.descriptive_name or route_path
-        await start_trace(trace_path, {"__location__": "library_client"})
-        try:
-            result = await matched_func(**body)
-        finally:
-            await end_trace()
+        result = await matched_func(**body)
 
         # Handle FastAPI Response objects (e.g., from file content retrieval)
         if isinstance(result, FastAPIResponse):
@@ -448,19 +433,13 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
 
         body = self._convert_body(path, options.method, body)
 
-        trace_path = webmethod.descriptive_name or route_path
-        await start_trace(trace_path, {"__location__": "library_client"})
-
         async def gen():
-            try:
-                async for chunk in await func(**body):
-                    data = json.dumps(convert_pydantic_to_json_value(chunk))
-                    sse_event = f"data: {data}\n\n"
-                    yield sse_event.encode("utf-8")
-            finally:
-                await end_trace()
+            async for chunk in await func(**body):
+                data = json.dumps(convert_pydantic_to_json_value(chunk))
+                sse_event = f"data: {data}\n\n"
+                yield sse_event.encode("utf-8")
 
-        wrapped_gen = preserve_contexts_async_generator(gen(), [CURRENT_TRACE_CONTEXT, PROVIDER_DATA_VAR])
+        wrapped_gen = preserve_contexts_async_generator(gen(), [PROVIDER_DATA_VAR])
 
         mock_response = httpx.Response(
             status_code=httpx.codes.OK,

llama_stack/core/server/server.py

@@ -58,14 +58,6 @@ from llama_stack.core.utils.config_resolution import Mode, resolve_config_or_dis
 from llama_stack.core.utils.context import preserve_contexts_async_generator
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api
-from llama_stack.providers.inline.telemetry.meta_reference.config import TelemetryConfig
-from llama_stack.providers.inline.telemetry.meta_reference.telemetry import (
-    TelemetryAdapter,
-)
-from llama_stack.providers.utils.telemetry.tracing import (
-    CURRENT_TRACE_CONTEXT,
-    setup_logger,
-)
 
 from .auth import AuthenticationMiddleware
 from .quota import QuotaMiddleware
@@ -237,9 +229,7 @@ def create_dynamic_typed_route(func: Any, method: str, route: str) -> Callable:
 
             try:
                 if is_streaming:
-                    gen = preserve_contexts_async_generator(
-                        sse_generator(func(**kwargs)), [CURRENT_TRACE_CONTEXT, PROVIDER_DATA_VAR]
-                    )
+                    gen = preserve_contexts_async_generator(sse_generator(func(**kwargs)), [PROVIDER_DATA_VAR])
                     return StreamingResponse(gen, media_type="text/event-stream")
                 else:
                     value = func(**kwargs)
@@ -408,11 +398,6 @@ def create_app() -> StackApp:
         if cors_config:
             app.add_middleware(CORSMiddleware, **cors_config.model_dump())
 
-    if Api.telemetry in impls:
-        setup_logger(impls[Api.telemetry])
-    else:
-        setup_logger(TelemetryAdapter(TelemetryConfig(), {}))
-
     # Load external APIs if configured
     external_apis = load_external_apis(config)
     all_routes = get_all_api_routes(external_apis)