Verify exact production traces and record rollout

infra/docker/docker-compose.observability.yml

@@ -0,0 +1,62 @@
+# Optional overlay for the existing EC2 production Compose topology:
+# docker compose -f docker-compose.prod.yml -f docker-compose.observability.yml up -d
+# The base production file remains unchanged and does not require this stack.
+services:
+  ai-service:
+    environment:
+      OTEL_ENABLED: "true"
+      OTEL_SERVICE_NAME: ai-service
+      OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318/v1/traces
+      ENVIRONMENT: compose
+    depends_on:
+      - otel-collector
+
+  prometheus:
+    image: prom/prometheus:v3.3.0
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.path=/prometheus
+      - --enable-feature=exemplar-storage
+    volumes:
+      - ./prometheus/prometheus-compose.yml:/etc/prometheus/prometheus.yml:ro
+      - prometheus-data:/prometheus
+    restart: unless-stopped
+
+  tempo:
+    image: grafana/tempo:2.7.2
+    command: ["-config.file=/etc/tempo/tempo.yml"]
+    volumes:
+      - ./tempo/tempo.yml:/etc/tempo/tempo.yml:ro
+      - tempo-data:/var/tempo
+    restart: unless-stopped
+
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:0.123.0
+    command: ["--config=/etc/otelcol/config.yml"]
+    volumes:
+      - ./otel/collector.yml:/etc/otelcol/config.yml:ro
+    depends_on:
+      - tempo
+    restart: unless-stopped
+
+  grafana:
+    image: grafana/grafana:11.5.2
+    ports:
+      - "3002:3000"
+    environment:
+      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-change-me}
+      GF_AUTH_ANONYMOUS_ENABLED: "false"
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+      - grafana-data:/var/lib/grafana
+    depends_on:
+      - prometheus
+      - tempo
+    restart: unless-stopped
+
+volumes:
+  prometheus-data:
+  tempo-data:
+  grafana-data: