feat: improve telemetry (#2590)

# What does this PR do?

* Use a single env variable to setup OTEL endpoint
* Update telemetry provider doc
* Update general telemetry doc with the metric with generate
* Left a script to setup telemetry for testing

Closes: https://github.com/meta-llama/llama-stack/issues/783

Note to reviewer: the `setup_telemetry.sh` script was useful for me, it
was nicely generated by AI, if we don't want it in the repo, and I can
delete it, and I would understand.

Signed-off-by: Sébastien Han <seb@redhat.com>

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

@@ -20,13 +20,9 @@ class TelemetrySink(StrEnum):
 
 
 class TelemetryConfig(BaseModel):
-    otel_trace_endpoint: str | None = Field(
+    otel_exporter_otlp_endpoint: str | None = Field(
         default=None,
-        description="The OpenTelemetry collector endpoint URL for traces",
-    )
-    otel_metric_endpoint: str | None = Field(
-        default=None,
-        description="The OpenTelemetry collector endpoint URL for metrics",
+        description="The OpenTelemetry collector endpoint URL (base URL for traces, metrics, and logs). If not set, the SDK will use OTEL_EXPORTER_OTLP_ENDPOINT environment variable.",
     )
     service_name: str = Field(
         # service name is always the same, use zero-width space to avoid clutter
@@ -35,7 +31,7 @@ class TelemetryConfig(BaseModel):
     )
     sinks: list[TelemetrySink] = Field(
         default=[TelemetrySink.CONSOLE, TelemetrySink.SQLITE],
-        description="List of telemetry sinks to enable (possible values: otel, sqlite, console)",
+        description="List of telemetry sinks to enable (possible values: otel_trace, otel_metric, sqlite, console)",
     )
     sqlite_db_path: str = Field(
         default_factory=lambda: (RUNTIME_BASE_DIR / "trace_store.db").as_posix(),
@@ -55,4 +51,5 @@ class TelemetryConfig(BaseModel):
             "service_name": "${env.OTEL_SERVICE_NAME:=\u200b}",
             "sinks": "${env.TELEMETRY_SINKS:=console,sqlite}",
             "sqlite_db_path": "${env.SQLITE_STORE_DIR:=" + __distro_dir__ + "}/" + db_name,
+            "otel_exporter_otlp_endpoint": "${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}",
         }

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

@@ -86,24 +86,27 @@ class TelemetryAdapter(TelemetryDatasetMixin, Telemetry):
             provider = TracerProvider(resource=resource)
             trace.set_tracer_provider(provider)
             _TRACER_PROVIDER = provider
-            if TelemetrySink.OTEL_TRACE in self.config.sinks:
-                if self.config.otel_trace_endpoint is None:
-                    raise ValueError("otel_trace_endpoint is required when OTEL_TRACE is enabled")
-                span_exporter = OTLPSpanExporter(
-                    endpoint=self.config.otel_trace_endpoint,
-                )
-                span_processor = BatchSpanProcessor(span_exporter)
-                trace.get_tracer_provider().add_span_processor(span_processor)
-            if TelemetrySink.OTEL_METRIC in self.config.sinks:
-                if self.config.otel_metric_endpoint is None:
-                    raise ValueError("otel_metric_endpoint is required when OTEL_METRIC is enabled")
-                metric_reader = PeriodicExportingMetricReader(
-                    OTLPMetricExporter(
-                        endpoint=self.config.otel_metric_endpoint,
+
+            # Use single OTLP endpoint for all telemetry signals
+            if TelemetrySink.OTEL_TRACE in self.config.sinks or TelemetrySink.OTEL_METRIC in self.config.sinks:
+                if self.config.otel_exporter_otlp_endpoint is None:
+                    raise ValueError(
+                        "otel_exporter_otlp_endpoint is required when OTEL_TRACE or OTEL_METRIC is enabled"
                     )
-                )
-                metric_provider = MeterProvider(resource=resource, metric_readers=[metric_reader])
-                metrics.set_meter_provider(metric_provider)
+
+                # Let OpenTelemetry SDK handle endpoint construction automatically
+                # The SDK will read OTEL_EXPORTER_OTLP_ENDPOINT and construct appropriate URLs
+                # https://opentelemetry.io/docs/languages/sdk-configuration/otlp-exporter
+                if TelemetrySink.OTEL_TRACE in self.config.sinks:
+                    span_exporter = OTLPSpanExporter()
+                    span_processor = BatchSpanProcessor(span_exporter)
+                    trace.get_tracer_provider().add_span_processor(span_processor)
+
+                if TelemetrySink.OTEL_METRIC in self.config.sinks:
+                    metric_reader = PeriodicExportingMetricReader(OTLPMetricExporter())
+                    metric_provider = MeterProvider(resource=resource, metric_readers=[metric_reader])
+                    metrics.set_meter_provider(metric_provider)
+
             if TelemetrySink.SQLITE in self.config.sinks:
                 trace.get_tracer_provider().add_span_processor(SQLiteSpanProcessor(self.config.sqlite_db_path))
             if TelemetrySink.CONSOLE in self.config.sinks: