fix: remove custom tracing middleware

llama_stack/core/server/server.py

@@ -61,6 +61,7 @@
 from llama_stack.providers.inline.telemetry.meta_reference.config import TelemetryConfig
 from llama_stack.providers.inline.telemetry.meta_reference.telemetry import (
     TelemetryAdapter,
+    fastapi_telemetry_middleware,
 )
 from llama_stack.providers.utils.telemetry.tracing import (
     CURRENT_TRACE_CONTEXT,
@@ -69,7 +70,6 @@
 
 from .auth import AuthenticationMiddleware
 from .quota import QuotaMiddleware
-from .tracing import TracingMiddleware
 
 REPO_ROOT = Path(__file__).parent.parent.parent.parent
 
@@ -452,6 +452,7 @@ def create_app() -> StackApp:
 
     if config.telemetry.enabled:
         setup_logger(impls[Api.telemetry])
+        fastapi_telemetry_middleware(app)
     else:
         setup_logger(TelemetryAdapter(TelemetryConfig(), {}))
 
@@ -511,8 +512,6 @@ def create_app() -> StackApp:
     app.exception_handler(RequestValidationError)(global_exception_handler)
     app.exception_handler(Exception)(global_exception_handler)
 
-    app.add_middleware(TracingMiddleware, impls=impls, external_apis=external_apis)
-
     return app
 
 

llama_stack/providers/inline/telemetry/meta_reference/telemetry.py

@@ -8,9 +8,11 @@
 import threading
 from typing import Any
 
+from fastapi import FastAPI
 from opentelemetry import metrics, trace
 from opentelemetry.exporter.otlp.proto.http.metric_exporter import OTLPMetricExporter
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor
 from opentelemetry.sdk.metrics import MeterProvider
 from opentelemetry.sdk.metrics.export import PeriodicExportingMetricReader
 from opentelemetry.sdk.trace import TracerProvider
@@ -250,3 +252,10 @@ def _log_structured(self, event: StructuredLogEvent, ttl_seconds: int) -> None:
                     _GLOBAL_STORAGE["active_spans"].pop(span_id, None)
             else:
                 raise ValueError(f"Unknown structured log event: {event}")
+
+
+def fastapi_telemetry_middleware(app: FastAPI):
+    """
+    Instrument the FastAPI app with OpenTelemetry.
+    """
+    FastAPIInstrumentor.instrument_app(app)

pyproject.toml

@@ -25,30 +25,31 @@ classifiers = [
 ]
 dependencies = [
     "aiohttp",
-    "fastapi>=0.115.0,<1.0",                          # server
-    "fire",                                           # for MCP in LLS client
+    "fastapi>=0.115.0,<1.0", # server
+    "fire", # for MCP in LLS client
     "httpx",
     "jinja2>=3.1.6",
     "jsonschema",
     "llama-stack-client>=0.3.0",
-    "openai>=1.107",                                  # for expires_after support
+    "openai>=1.107", # for expires_after support
     "prompt-toolkit",
     "python-dotenv",
-    "pyjwt[crypto]>=2.10.0",                          # Pull crypto to support RS256 for jwt. Requires 2.10.0+ for ssl_context support.
+    "pyjwt[crypto]>=2.10.0", # Pull crypto to support RS256 for jwt. Requires 2.10.0+ for ssl_context support.
     "pydantic>=2.11.9",
     "rich",
     "starlette",
     "termcolor",
     "tiktoken",
     "pillow",
     "h11>=0.16.0",
-    "python-multipart>=0.0.20",                       # For fastapi Form
-    "uvicorn>=0.34.0",                                # server
-    "opentelemetry-sdk>=1.30.0",                      # server
+    "python-multipart>=0.0.20", # For fastapi Form
+    "uvicorn>=0.34.0", # server
+    "opentelemetry-sdk>=1.30.0", # server
     "opentelemetry-exporter-otlp-proto-http>=1.30.0", # server
-    "aiosqlite>=0.21.0",                              # server - for metadata store
-    "asyncpg",                                        # for metadata store
-    "sqlalchemy[asyncio]>=2.0.41",                    # server - for conversations
+    "aiosqlite>=0.21.0", # server - for metadata store
+    "asyncpg", # for metadata store
+    "sqlalchemy[asyncio]>=2.0.41", # server - for conversations
+    "opentelemetry-instrumentation-fastapi>=0.57b0",
 ]
 
 [project.optional-dependencies]