Add observability module: Spring AI built-in meters and spans, cost per endpoint from token usage, Prometheus and Grafana dashboard

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01JXVi2GMQ7bR5EmbUFdDj7N
2026-10-09 06:39:21 +00:00
parent 65f580c5bc
commit cc2a1b8bcb
45 changed files with 1731 additions and 0 deletions
@@ -0,0 +1,11 @@
+# Profile used by scripts/stack-up.sh: adds the latency histogram Grafana needs for percentiles.
+management:
+  metrics:
+    distribution:
+      percentiles-histogram:
+        gen_ai.client.operation: true
+        spring.ai.chat.client: true
+      minimum-expected-value:
+        gen_ai.client.operation: 50ms
+      maximum-expected-value:
+        gen_ai.client.operation: 30s