feat(prom): add cadvisor/nvidia/tempo targets, drop jaeger

infra/prometheus/targets/services.yml

@@ -8,16 +8,27 @@
     job: traefik
     __metrics_path__: /metrics
 
-# Jaeger
+# Tempo
-- targets: ['jaeger:14269']
+- targets: ['tempo:3200']
   labels:
-    job: jaeger
+    job: tempo
+    __metrics_path__: /metrics
 
 # Loki
 - targets: ['loki:3100']
   labels:
     job: loki
 
+# cAdvisor
+- targets: ['cadvisor:8080']
+  labels:
+    job: cadvisor
+
+# NVIDIA GPU (DCGM)
+- targets: ['nvidia-exporter:9400']
+  labels:
+    job: nvidia-gpu
+
 # Nessie
 - targets: ['nessie:9000']
   labels:

tests/test_observability.py

@@ -139,3 +139,14 @@ class TestOtelTempo:
         traces = cfg["service"]["pipelines"]["traces"]
         assert "otlp_http/tempo" in traces["exporters"]
         assert "memory_limiter" in traces["processors"]
+
+
+class TestPrometheusTargets:
+    def test_targets_swap_jaeger_for_tempo_and_add_exporters(self):
+        path = ROOT / "infra/prometheus/targets/services.yml"
+        targets = yaml.safe_load(path.read_text())
+        jobs = {entry["labels"]["job"] for entry in targets if "labels" in entry}
+        assert "tempo" in jobs
+        assert "cadvisor" in jobs
+        assert "nvidia-gpu" in jobs
+        assert "jaeger" not in jobs