llama-cpp: integrate native prometheus /metrics endpoint

llama.cpp server has a built-in /metrics endpoint exposing
prompt_tokens_seconds, predicted_tokens_seconds, tokens_predicted_total,
n_decode_total, and n_busy_slots_per_decode. Enable it with --metrics
and add a Prometheus scrape target, replacing the need for any external
metric collection for LLM inference monitoring.

services/grafana/prometheus.nix

@@ -65,6 +65,12 @@ in
           { targets = [ "127.0.0.1:${toString service_configs.ports.private.prometheus_apcupsd.port}" ]; }
         ];
       }
+      {
+        job_name = "llama-cpp";
+        static_configs = [
+          { targets = [ "127.0.0.1:${toString service_configs.ports.private.llama_cpp.port}" ]; }
+        ];
+      }
     ];
   };
 

services/llama-cpp/llama-cpp.nix

@@ -35,6 +35,7 @@ in
       "on"
       "--api-key-file"
       config.age.secrets.llama-cpp-api-key.path
+      "--metrics"
     ];
   };