monitoring02: enable alerting and migrate CNAMEs from http-proxy

- Switch vmalert from blackhole mode to sending alerts to local
  Alertmanager
- Import alerttonotify service so alerts route to NATS notifications
- Move alertmanager and grafana CNAMEs from http-proxy to monitoring02
- Add monitoring CNAME to monitoring02
- Add Caddy reverse proxy entries for alertmanager and grafana
- Remove prometheus, alertmanager, and grafana Caddy entries from
  http-proxy (now served directly by monitoring02)
- Move monitoring02 Vault AppRole to hosts-generated.tf and add
  shared/nats/nkey access and prometheus-metrics policy
- Add extra_policies support to generated host AppRoles

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

hosts/http-proxy/configuration.nix

@@ -18,9 +18,6 @@
     "sonarr"
     "ha"
     "z2m"
-    "grafana"
-    "prometheus"
-    "alertmanager"
     "jelly"
     "pyroscope"
     "pushgw"

hosts/monitoring02/configuration.nix

@@ -18,7 +18,7 @@
     role = "monitoring";
   };
 
-  homelab.dns.cnames = [ "grafana-test" "metrics" "vmalert" "loki" ];
+  homelab.dns.cnames = [ "monitoring" "alertmanager" "grafana" "grafana-test" "metrics" "vmalert" "loki" ];
 
   # Enable Vault integration
   vault.enable = true;

hosts/monitoring02/default.nix

@@ -4,5 +4,6 @@
     ../../services/grafana
     ../../services/victoriametrics
     ../../services/loki
+    ../../services/monitoring/alerttonotify.nix
   ];
 }

services/grafana/default.nix

@@ -91,6 +91,14 @@
       acme_ca https://vault.home.2rjus.net:8200/v1/pki_int/acme/directory
       metrics
     '';
+    virtualHosts."grafana.home.2rjus.net".extraConfig = ''
+      log {
+        output file /var/log/caddy/grafana.log {
+          mode 644
+        }
+      }
+      reverse_proxy http://127.0.0.1:3000
+    '';
     virtualHosts."grafana-test.home.2rjus.net".extraConfig = ''
       log {
         output file /var/log/caddy/grafana.log {

services/http-proxy/proxy.nix

@@ -54,30 +54,7 @@
         }
         reverse_proxy http://ha1.home.2rjus.net:8080
       }
-      prometheus.home.2rjus.net {
+
-        log {
-          output file /var/log/caddy/prometheus.log {
-            mode 644
-          }
-        }
-        reverse_proxy http://monitoring01.home.2rjus.net:9090
-      }
-      alertmanager.home.2rjus.net {
-        log {
-          output file /var/log/caddy/alertmanager.log {
-            mode 644
-          }
-        }
-        reverse_proxy http://monitoring01.home.2rjus.net:9093
-      }
-      grafana.home.2rjus.net {
-        log {
-          output file /var/log/caddy/grafana.log {
-            mode 644
-          }
-        }
-        reverse_proxy http://monitoring01.home.2rjus.net:3000
-      }
       jelly.home.2rjus.net {
         log {
           output file /var/log/caddy/jelly.log {

services/victoriametrics/default.nix

@@ -170,15 +170,12 @@ in
     };
   };
 
-  # vmalert for alerting rules - no notifier during parallel operation
+  # vmalert for alerting rules
   services.vmalert.instances.default = {
     enable = true;
     settings = {
       "datasource.url" = "http://localhost:8428";
-      # Blackhole notifications during parallel operation to prevent duplicate alerts.
+      "notifier.url" = [ "http://localhost:9093" ];
-      # Replace with notifier.url after cutover from monitoring01:
-      # "notifier.url" = [ "http://localhost:9093" ];
-      "notifier.blackhole" = true;
       "rule" = [ ../monitoring/rules.yml ];
     };
   };
@@ -191,8 +188,11 @@ in
     reverse_proxy http://127.0.0.1:8880
   '';
 
-  # Alertmanager - same config as monitoring01 but will only receive
+  # Alertmanager
-  # alerts after cutover (vmalert notifier is disabled above)
+  services.caddy.virtualHosts."alertmanager.home.2rjus.net".extraConfig = ''
+    reverse_proxy http://127.0.0.1:9093
+  '';
+
   services.prometheus.alertmanager = {
     enable = true;
     configuration = {

terraform/vault/approle.tf

@@ -115,15 +115,6 @@ locals {
       ]
     }
 
-    # monitoring02: Grafana + VictoriaMetrics
-    "monitoring02" = {
-      paths = [
-        "secret/data/hosts/monitoring02/*",
-        "secret/data/hosts/monitoring01/apiary-token",
-        "secret/data/services/grafana/*",
-      ]
-    }
-
   }
 }
 

terraform/vault/hosts-generated.tf

@@ -44,6 +44,15 @@ locals {
         "secret/data/hosts/garage01/*",
       ]
     }
+    "monitoring02" = {
+      paths = [
+        "secret/data/hosts/monitoring02/*",
+        "secret/data/hosts/monitoring01/apiary-token",
+        "secret/data/services/grafana/*",
+        "secret/data/shared/nats/nkey",
+      ]
+      extra_policies = ["prometheus-metrics"]
+    }
 
   }
 
@@ -74,7 +83,10 @@ resource "vault_approle_auth_backend_role" "generated_hosts" {
 
   backend            = vault_auth_backend.approle.path
   role_name          = each.key
-  token_policies     = ["host-${each.key}", "homelab-deploy", "nixos-exporter", "loki-push"]
+  token_policies     = concat(
+    ["host-${each.key}", "homelab-deploy", "nixos-exporter", "loki-push"],
+    lookup(each.value, "extra_policies", [])
+  )
   secret_id_ttl      = 0 # Never expire (wrapped tokens provide time limit)
   token_ttl          = 3600
   token_max_ttl      = 3600