Propagate traces over HTTP and add Redis spans

setup_telemetry now instruments httpx and redis process-wide. Both patch
the client classes, so clients created at import time (gateway's
_proxy_client, common.redis_client) are covered too. httpx CLIENT spans
inject traceparent, so the downstream FastAPI SERVER spans join the
caller's trace. gateway and fraud get setup_telemetry, the FastAPI span,
and the OTLP auth header. All seven services now export traces.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

common/telemetry.py

@@ -3,6 +3,8 @@ from opentelemetry.sdk.resources import SERVICE_NAME, Resource
 from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.instrumentation.httpx import HTTPXClientInstrumentor
+from opentelemetry.instrumentation.redis import RedisInstrumentor
 
 
 def setup_telemetry(service_name: str):
@@ -11,3 +13,8 @@ def setup_telemetry(service_name: str):
     provider = TracerProvider(resource=resource)
     provider.add_span_processor(processor)
     trace.set_tracer_provider(provider)
+
+    # Process-wide patches on the client classes, so they also cover clients
+    # created at import time (gateway's _proxy_client, common.redis_client).
+    HTTPXClientInstrumentor().instrument()
+    RedisInstrumentor().instrument()

docker-compose.yml

@@ -86,6 +86,8 @@ services:
     environment:
       <<: *app-env
       SERVICE_NAME: gateway
+    env_file:
+      - .env.observability
     command: uvicorn services.gateway.app:app --host 0.0.0.0 --port 8000 --reload --no-access-log
     ports:
       - "8000:8000"
@@ -128,6 +130,8 @@ services:
     environment:
       <<: *app-env
       SERVICE_NAME: fraud
+    env_file:
+      - .env.observability
     command: uvicorn services.fraud.app:app --host 0.0.0.0 --port 8002 --reload --no-access-log
     ports:
       - "8002:8002"

services/fraud/app.py

@@ -2,19 +2,28 @@ import httpx
 from fastapi import FastAPI, Request
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel
+from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor
 
 from common.http import downstream_client
 from common.logging_config import configure_logging
 from common.redis_client import redis_client
 from common.settings import settings
+from common.telemetry import setup_telemetry
 
 from . import chaos
 from .scoring import score
 
 SERVICE_NAME = "fraud"
 logger = configure_logging(SERVICE_NAME)
+setup_telemetry(service_name=SERVICE_NAME)
 app = FastAPI(title=SERVICE_NAME)
 
+FastAPIInstrumentor.instrument_app(
+    app,
+    excluded_urls="/healthz",
+    exclude_spans=["receive", "send"],
+)
+
 
 class ScoreRequest(BaseModel):
     account_id: str

services/gateway/app.py

@@ -7,18 +7,27 @@ from fastapi import FastAPI, Request
 from fastapi.responses import FileResponse, JSONResponse
 from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel, field_validator
+from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor
 
 from common.chaos_flags import ALL_FLAGS, get_flags, set_flag, set_profile
 from common.logging_config import configure_logging
 from common.settings import settings
+from common.telemetry import setup_telemetry
 
 from . import orchestrator
 from .orchestrator import UpstreamFailure
 
 SERVICE_NAME = "gateway"
 logger = configure_logging(SERVICE_NAME)
+setup_telemetry(service_name=SERVICE_NAME)
 app = FastAPI(title=SERVICE_NAME)
 
+FastAPIInstrumentor.instrument_app(
+    app,
+    excluded_urls="/healthz",
+    exclude_spans=["receive", "send"],
+)
+
 STATIC_DIR = Path(__file__).parent / "static"
 app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")