llama-cpp: add grafana annotations for inference requests

Poll /slots endpoint, create annotations when slots start processing,
close with token count when complete. Includes NixOS VM test with
mock llama-cpp and grafana servers. Dashboard annotation entry added.

services/monitoring.nix

@@ -120,6 +120,18 @@ let
         type = "tags";
         tags = [ "zfs-scrub" ];
       }
+      {
+        name = "LLM Requests";
+        datasource = {
+          type = "grafana";
+          uid = "-- Grafana --";
+        };
+        enable = true;
+        iconColor = "purple";
+        showIn = 0;
+        type = "tags";
+        tags = [ "llama-cpp" ];
+      }
     ];
 
     panels = [