diff --git a/infrastructure-monitoring.prose.md b/infrastructure-monitoring.prose.md index 5c7828b..205aa03 100644 --- a/infrastructure-monitoring.prose.md +++ b/infrastructure-monitoring.prose.md @@ -122,6 +122,18 @@ curl -s http://192.168.68.8:9400/metrics && echo " - OK" || echo " - FAIL" curl -s http://192.168.68.110:9400/metrics && echo " - OK" || echo " - FAIL" curl -s http://192.168.68.15:9400/metrics && echo " - OK" || echo " - FAIL" +# Router health (via nginx on port 80) +curl -s -o /dev/null -w '%{http_code}' http://192.168.68.116/health +# Expected: 200 (Router is up and responding) + +# LiteLLM health (via nginx on port 80) +curl -s -o /dev/null -w '%{http_code}' http://192.168.68.116/litellm/health +# Expected: 200 (LiteLLM is up and responding) + +# PVE API (401 expected for unauthenticated probe — API is up over https) +curl -s -o /dev/null -w '%{http_code}' https://192.168.68.116:8006/api2/json +# Expected: 401 (unauthorized — API is up; 000 = unreachable, 500 = API down) + # Prometheus targets curl -s http://192.168.68.116:9090/api/v1/targets | jq '.data.activeTargets' # Expected: All targets UP (may show some down if exporters not deployed) @@ -130,7 +142,7 @@ curl -s http://192.168.68.116:9090/api/v1/targets | jq '.data.activeTargets' curl -s http://192.168.68.116:3001/api/health | jq '{status, version}' # Expected: {"status":"ok","version":"..."} -# LiteLLM metrics +# LiteLLM metrics (Prometheus endpoint) curl -s http://192.168.68.116:4001/metrics | head -20 # Expected: Prometheus-formatted metrics output ```