caddy: wildcard TLS via DNS-01 challenge + ddns-updater for Njalla

Build Caddy with the caddy-dns/njalla plugin to enable DNS-01 ACME challenges. This issues a single wildcard certificate for *.sigkill.computer instead of per-subdomain certificates, reducing Let's Encrypt API calls and certificate management overhead. Add ddns-updater service (nixpkgs services.ddns-updater) configured with Njalla provider to automatically update DNS records when the server's public IP changes.
grafana: replace llama-cpp-annotations daemon with prometheus query
2026-04-09 19:54:57 -04:00 · 2026-04-09 19:54:57 -04:00 · 2026-04-09 19:54:57 -04:00 · 2026-04-09 19:54:57 -04:00
39 changed files with 290 additions and 623 deletions
--- a/configuration.nix
+++ b/configuration.nix
@@ -71,6 +71,8 @@
    ./services/mollysocket.nix

    ./services/harmonia.nix
+
+    ./services/ddns-updater.nix
  ];

  # Hosts entries for CI/CD deploy targets
--- a/modules/age-secrets.nix
+++ b/modules/age-secrets.nix
@@ -46,6 +46,20 @@
      group = "caddy";
    };

+    # Njalla API token (NJALLA_API_TOKEN=...) for Caddy DNS-01 challenge
+    njalla-api-token-env = {
+      file = ../secrets/njalla-api-token-env.age;
+      mode = "0400";
+      owner = "caddy";
+      group = "caddy";
+    };
+
+    # ddns-updater config.json with Njalla provider credentials
+    ddns-updater-config = {
+      file = ../secrets/ddns-updater-config.age;
+      mode = "0400";
+    };
+
    jellyfin-api-key = {
      file = ../secrets/jellyfin-api-key.age;
      mode = "0400";
--- a/modules/lib.nix
+++ b/modules/lib.nix
@@ -59,8 +59,12 @@ inputs.nixpkgs.lib.extend (
      { pkgs, config, ... }:
      {
        systemd.services."${serviceName}-mounts" = {
-          wants = [ "zfs.target" ] ++ lib.optionals (zpool != "") [ "zfs-import-${zpool}.service" ];
-          after = lib.optionals (zpool != "") [ "zfs-import-${zpool}.service" ];
+          wants = [
+            "zfs.target"
+            "zfs-mount.service"
+          ]
+          ++ lib.optionals (zpool != "") [ "zfs-import-${zpool}.service" ];
+          after = [ "zfs-mount.service" ] ++ lib.optionals (zpool != "") [ "zfs-import-${zpool}.service" ];
          before = [ "${serviceName}.service" ];

          serviceConfig = {
@@ -176,5 +180,108 @@ inputs.nixpkgs.lib.extend (
          after = [ "${serviceName}-file-perms.service" ];
        };
      };
+    # Creates a Caddy virtualHost with reverse_proxy to a local or VPN-namespaced port.
+    # Use `subdomain` for "<name>.${domain}" or `domain` for a full custom domain.
+    # Exactly one of `subdomain` or `domain` must be provided.
+    mkCaddyReverseProxy =
+      {
+        subdomain ? null,
+        domain ? null,
+        port,
+        auth ? false,
+        vpn ? false,
+      }:
+      assert (subdomain != null) != (domain != null);
+      { config, ... }:
+      let
+        vhostDomain = if domain != null then domain else "${subdomain}.${service_configs.https.domain}";
+        upstream =
+          if vpn then
+            "${config.vpnNamespaces.wg.namespaceAddress}:${builtins.toString port}"
+          else
+            ":${builtins.toString port}";
+      in
+      {
+        services.caddy.virtualHosts."${vhostDomain}".extraConfig = lib.concatStringsSep "\n" (
+          lib.optional auth "import ${config.age.secrets.caddy_auth.path}" ++ [ "reverse_proxy ${upstream}" ]
+        );
+      };
+
+    # Creates a fail2ban jail with systemd journal backend.
+    # Covers the common pattern: journal-based detection, http/https ports, default thresholds.
+    mkFail2banJail =
+      {
+        name,
+        unitName ? "${name}.service",
+        failregex,
+      }:
+      { ... }:
+      {
+        services.fail2ban.jails.${name} = {
+          enabled = true;
+          settings = {
+            backend = "systemd";
+            port = "http,https";
+            # defaults: maxretry=5, findtime=10m, bantime=10m
+          };
+          filter.Definition = {
+            inherit failregex;
+            ignoreregex = "";
+            journalmatch = "_SYSTEMD_UNIT=${unitName}";
+          };
+        };
+      };
+
+    # Creates a hardened Grafana annotation daemon service.
+    # Provides DynamicUser, sandboxing, state directory, and GRAFANA_URL/STATE_FILE automatically.
+    mkGrafanaAnnotationService =
+      {
+        name,
+        description,
+        script,
+        after ? [ ],
+        environment ? { },
+        loadCredential ? null,
+      }:
+      {
+        systemd.services."${name}-annotations" = {
+          inherit description;
+          after = [
+            "network.target"
+            "grafana.service"
+          ]
+          ++ after;
+          wantedBy = [ "multi-user.target" ];
+          serviceConfig = {
+            ExecStart = "${pkgs.python3}/bin/python3 ${script}";
+            Restart = "always";
+            RestartSec = "10s";
+            DynamicUser = true;
+            StateDirectory = "${name}-annotations";
+            NoNewPrivileges = true;
+            ProtectSystem = "strict";
+            ProtectHome = true;
+            PrivateTmp = true;
+            RestrictAddressFamilies = [
+              "AF_INET"
+              "AF_INET6"
+            ];
+            MemoryDenyWriteExecute = true;
+          }
+          // lib.optionalAttrs (loadCredential != null) {
+            LoadCredential = loadCredential;
+          };
+          environment = {
+            GRAFANA_URL = "http://127.0.0.1:${toString service_configs.ports.private.grafana.port}";
+            STATE_FILE = "/var/lib/${name}-annotations/state.json";
+          }
+          // environment;
+        };
+      };
+
+    # Shell command to extract an API key from an *arr config.xml file.
+    # Returns a string suitable for $() command substitution in shell scripts.
+    extractArrApiKey =
+      configXmlPath: "${lib.getExe pkgs.gnugrep} -oP '(?<=<ApiKey>)[^<]+' ${configXmlPath}";
  }
 )
--- a/secrets/ddns-updater-config.age
+++ b/secrets/ddns-updater-config.age
--- a/secrets/njalla-api-token-env.age
+++ b/secrets/njalla-api-token-env.age
--- a/service-configs.nix
+++ b/service-configs.nix
@@ -189,6 +189,10 @@ rec {
        port = 9563;
        proto = "tcp";
      };
+      prometheus_zfs = {
+        port = 9134;
+        proto = "tcp";
+      };
      harmonia = {
        port = 5500;
        proto = "tcp";
--- a/services/arr/arr-search.nix
+++ b/services/arr/arr-search.nix
@@ -1,5 +1,6 @@
 {
  pkgs,
+  lib,
  service_configs,
  ...
 }:
@@ -12,7 +13,6 @@ let

  curl = "${pkgs.curl}/bin/curl";
  jq = "${pkgs.jq}/bin/jq";
-  grep = "${pkgs.gnugrep}/bin/grep";

  # Max items to search per cycle per category (missing + cutoff) per app
  maxPerCycle = 5;
@@ -20,8 +20,8 @@ let
  searchScript = pkgs.writeShellScript "arr-search" ''
    set -euo pipefail

-    RADARR_KEY=$(${grep} -oP '(?<=<ApiKey>)[^<]+' ${radarrConfig})
-    SONARR_KEY=$(${grep} -oP '(?<=<ApiKey>)[^<]+' ${sonarrConfig})
+    RADARR_KEY=$(${lib.extractArrApiKey radarrConfig})
+    SONARR_KEY=$(${lib.extractArrApiKey sonarrConfig})

    search_radarr() {
      local endpoint="$1"
--- a/services/arr/bazarr.nix
+++ b/services/arr/bazarr.nix
@@ -16,6 +16,11 @@
    (lib.serviceFilePerms "bazarr" [
      "Z ${service_configs.bazarr.dataDir} 0700 ${config.services.bazarr.user} ${config.services.bazarr.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "bazarr";
+      port = service_configs.ports.private.bazarr.port;
+      auth = true;
+    })
  ];

  services.bazarr = {
@@ -23,11 +28,6 @@
    listenPort = service_configs.ports.private.bazarr.port;
  };

-  services.caddy.virtualHosts."bazarr.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${builtins.toString service_configs.ports.private.bazarr.port}
-  '';
-
  users.users.${config.services.bazarr.user}.extraGroups = [
    service_configs.media_group
  ];
--- a/services/arr/jellyseerr.nix
+++ b/services/arr/jellyseerr.nix
@@ -13,6 +13,10 @@
    (lib.serviceFilePerms "jellyseerr" [
      "Z ${service_configs.jellyseerr.configDir} 0700 jellyseerr jellyseerr"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "jellyseerr";
+      port = service_configs.ports.private.jellyseerr.port;
+    })
  ];

  services.jellyseerr = {
@@ -36,8 +40,4 @@

  users.groups.jellyseerr = { };

-  services.caddy.virtualHosts."jellyseerr.${service_configs.https.domain}".extraConfig = ''
-    # import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${builtins.toString service_configs.ports.private.jellyseerr.port}
-  '';
 }
--- a/services/arr/prowlarr.nix
+++ b/services/arr/prowlarr.nix
@@ -14,6 +14,12 @@
    (lib.serviceFilePerms "prowlarr" [
      "Z ${service_configs.prowlarr.dataDir} 0700 prowlarr prowlarr"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "prowlarr";
+      port = service_configs.ports.private.prowlarr.port;
+      auth = true;
+      vpn = true;
+    })
  ];

  services.prowlarr = {
@@ -51,8 +57,4 @@
    ExecStart = lib.mkForce "${lib.getExe pkgs.prowlarr} -nobrowser -data=${service_configs.prowlarr.dataDir}";
  };

-  services.caddy.virtualHosts."prowlarr.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy ${config.vpnNamespaces.wg.namespaceAddress}:${builtins.toString service_configs.ports.private.prowlarr.port}
-  '';
 }
--- a/services/arr/radarr.nix
+++ b/services/arr/radarr.nix
@@ -16,6 +16,11 @@
    (lib.serviceFilePerms "radarr" [
      "Z ${service_configs.radarr.dataDir} 0700 ${config.services.radarr.user} ${config.services.radarr.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "radarr";
+      port = service_configs.ports.private.radarr.port;
+      auth = true;
+    })
  ];

  services.radarr = {
@@ -25,11 +30,6 @@
    settings.update.mechanism = "external";
  };

-  services.caddy.virtualHosts."radarr.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${builtins.toString service_configs.ports.private.radarr.port}
-  '';
-
  users.users.${config.services.radarr.user}.extraGroups = [
    service_configs.media_group
  ];
--- a/services/arr/recyclarr.nix
+++ b/services/arr/recyclarr.nix
@@ -13,8 +13,8 @@ let
  # Runs as root (via + prefix) after the NixOS module writes config.json.
  # Extracts API keys from radarr/sonarr config.xml and injects them via jq.
  injectApiKeys = pkgs.writeShellScript "recyclarr-inject-api-keys" ''
-    RADARR_KEY=$(${lib.getExe pkgs.gnugrep} -oP '(?<=<ApiKey>)[^<]+' ${radarrConfig})
-    SONARR_KEY=$(${lib.getExe pkgs.gnugrep} -oP '(?<=<ApiKey>)[^<]+' ${sonarrConfig})
+    RADARR_KEY=$(${lib.extractArrApiKey radarrConfig})
+    SONARR_KEY=$(${lib.extractArrApiKey sonarrConfig})
    ${pkgs.jq}/bin/jq \
      --arg rk "$RADARR_KEY" \
      --arg sk "$SONARR_KEY" \
--- a/services/arr/sonarr.nix
+++ b/services/arr/sonarr.nix
@@ -16,6 +16,11 @@
    (lib.serviceFilePerms "sonarr" [
      "Z ${service_configs.sonarr.dataDir} 0700 ${config.services.sonarr.user} ${config.services.sonarr.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "sonarr";
+      port = service_configs.ports.private.sonarr.port;
+      auth = true;
+    })
  ];

  systemd.tmpfiles.rules = [
@@ -31,11 +36,6 @@
    settings.update.mechanism = "external";
  };

-  services.caddy.virtualHosts."sonarr.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${builtins.toString service_configs.ports.private.sonarr.port}
-  '';
-
  users.users.${config.services.sonarr.user}.extraGroups = [
    service_configs.media_group
  ];
--- a/services/bitmagnet.nix
+++ b/services/bitmagnet.nix
@@ -8,6 +8,12 @@
 {
  imports = [
    (lib.vpnNamespaceOpenPort service_configs.ports.private.bitmagnet.port "bitmagnet")
+    (lib.mkCaddyReverseProxy {
+      subdomain = "bitmagnet";
+      port = service_configs.ports.private.bitmagnet.port;
+      auth = true;
+      vpn = true;
+    })
  ];

  services.bitmagnet = {
@@ -24,8 +30,4 @@
    };
  };

-  services.caddy.virtualHosts."bitmagnet.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy ${config.vpnNamespaces.wg.namespaceAddress}:${builtins.toString service_configs.ports.private.bitmagnet.port}
-  '';
 }
--- a/services/bitwarden.nix
+++ b/services/bitwarden.nix
@@ -13,6 +13,10 @@
    (lib.serviceFilePerms "vaultwarden" [
      "Z ${service_configs.vaultwarden.path} 0700 vaultwarden vaultwarden"
    ])
+    (lib.mkFail2banJail {
+      name = "vaultwarden";
+      failregex = ''^.*Username or password is incorrect\. Try again\. IP: <HOST>\..*$'';
+    })
  ];

  services.vaultwarden = {
@@ -38,18 +42,4 @@
    }
  '';

-  # Protect Vaultwarden login from brute force attacks
-  services.fail2ban.jails.vaultwarden = {
-    enabled = true;
-    settings = {
-      backend = "systemd";
-      port = "http,https";
-      # defaults: maxretry=5, findtime=10m, bantime=10m
-    };
-    filter.Definition = {
-      failregex = ''^.*Username or password is incorrect\. Try again\. IP: <HOST>\..*$'';
-      ignoreregex = "";
-      journalmatch = "_SYSTEMD_UNIT=vaultwarden.service";
-    };
-  };
 }
--- a/services/caddy/caddy.nix
+++ b/services/caddy/caddy.nix
@@ -56,9 +56,19 @@ in
    enable = true;
    email = "titaniumtown@proton.me";

-    # Enable on-demand TLS for old domain redirects
-    # Certs are issued dynamically when subdomains are accessed
+    # Build with Njalla DNS provider for DNS-01 ACME challenges (wildcard certs)
+    package = pkgs.caddy.withPlugins {
+      plugins = [ "github.com/caddy-dns/njalla@v0.0.0-20250823094507-f709141f1fe6" ];
+      hash = "sha256-rrOAR6noTDpV/I/hZXxhz0OXVJKu0mFQRq87RUrpmzw=";
+    };
+
    globalConfig = ''
+      # Wildcard cert for *.${newDomain} via DNS-01 challenge
+      acme_dns njalla {
+        api_token {env.NJALLA_API_TOKEN}
+      }
+
+      # On-demand TLS for old domain redirects
      on_demand_tls {
        ask http://localhost:9123/check
      }
@@ -106,6 +116,9 @@ in
    };
  };

+  # Inject Njalla API token for DNS-01 challenge
+  systemd.services.caddy.serviceConfig.EnvironmentFile = config.age.secrets.njalla-api-token-env.path;
+
  systemd.tmpfiles.rules = [
    "d ${config.services.caddy.dataDir} 700 ${config.services.caddy.user} ${config.services.caddy.group}"
  ];
--- a/services/ddns-updater.nix
+++ b/services/ddns-updater.nix
@@ -0,0 +1,14 @@
+{
+  config,
+  ...
+}:
+{
+  services.ddns-updater = {
+    enable = true;
+    environment = {
+      PERIOD = "5m";
+      # ddns-updater reads config from this path at runtime
+      CONFIG_FILEPATH = config.age.secrets.ddns-updater-config.path;
+    };
+  };
+}
--- a/services/firefox-syncserver.nix
+++ b/services/firefox-syncserver.nix
@@ -6,6 +6,13 @@
  ...
 }:
 {
+  imports = [
+    (lib.mkCaddyReverseProxy {
+      domain = service_configs.firefox_syncserver.domain;
+      port = service_configs.ports.private.firefox_syncserver.port;
+    })
+  ];
+
  services.firefox-syncserver = {
    enable = true;
    database = {
@@ -33,7 +40,4 @@
    ];
  };

-  services.caddy.virtualHosts."${service_configs.firefox_syncserver.domain}".extraConfig = ''
-    reverse_proxy :${builtins.toString service_configs.ports.private.firefox_syncserver.port}
-  '';
 }
--- a/services/gitea.nix
+++ b/services/gitea.nix
@@ -11,6 +11,14 @@
    (lib.serviceFilePerms "gitea" [
      "Z ${config.services.gitea.stateDir} 0700 ${config.services.gitea.user} ${config.services.gitea.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      domain = service_configs.gitea.domain;
+      port = service_configs.ports.private.gitea.port;
+    })
+    (lib.mkFail2banJail {
+      name = "gitea";
+      failregex = "^.*Failed authentication attempt for .* from <HOST>:.*$";
+    })
  ];

  services.gitea = {
@@ -41,10 +49,6 @@
    };
  };

-  services.caddy.virtualHosts."${service_configs.gitea.domain}".extraConfig = ''
-    reverse_proxy :${builtins.toString config.services.gitea.settings.server.HTTP_PORT}
-  '';
-
  services.postgresql = {
    ensureDatabases = [ config.services.gitea.user ];
    ensureUsers = [
@@ -58,18 +62,4 @@

  services.openssh.settings.AllowUsers = [ config.services.gitea.user ];

-  # Protect Gitea login from brute force attacks
-  services.fail2ban.jails.gitea = {
-    enabled = true;
-    settings = {
-      backend = "systemd";
-      port = "http,https";
-      # defaults: maxretry=5, findtime=10m, bantime=10m
-    };
-    filter.Definition = {
-      failregex = "^.*Failed authentication attempt for .* from <HOST>:.*$";
-      ignoreregex = "";
-      journalmatch = "_SYSTEMD_UNIT=gitea.service";
-    };
-  };
 }
--- a/services/grafana/dashboard.nix
+++ b/services/grafana/dashboard.nix
@@ -50,15 +50,12 @@ let
      }
      {
        name = "LLM Requests";
-        datasource = {
-          type = "grafana";
-          uid = "-- Grafana --";
-        };
+        datasource = promDs;
        enable = true;
        iconColor = "purple";
-        showIn = 0;
-        type = "tags";
-        tags = [ "llama-cpp" ];
+        expr = "llamacpp:requests_processing > 0";
+        step = "10s";
+        titleFormat = "LLM inference";
      }
    ];

@@ -613,13 +610,13 @@ let
        targets = [
          {
            datasource = promDs;
-            expr = "zpool_used_bytes{pool=\"tank\"} / zpool_size_bytes{pool=\"tank\"} * 100";
+            expr = "zfs_pool_allocated_bytes{pool=\"tank\"} / zfs_pool_size_bytes{pool=\"tank\"} * 100";
            legendFormat = "tank";
            refId = "A";
          }
          {
            datasource = promDs;
-            expr = "zpool_used_bytes{pool=\"hdds\"} / zpool_size_bytes{pool=\"hdds\"} * 100";
+            expr = "zfs_pool_allocated_bytes{pool=\"hdds\"} / zfs_pool_size_bytes{pool=\"hdds\"} * 100";
            legendFormat = "hdds";
            refId = "B";
          }
@@ -653,19 +650,19 @@ let
        targets = [
          {
            datasource = promDs;
-            expr = "partition_used_bytes{mount=\"/boot\"} / partition_size_bytes{mount=\"/boot\"} * 100";
+            expr = "(node_filesystem_size_bytes{mountpoint=\"/boot\"} - node_filesystem_avail_bytes{mountpoint=\"/boot\"}) / node_filesystem_size_bytes{mountpoint=\"/boot\"} * 100";
            legendFormat = "/boot";
            refId = "A";
          }
          {
            datasource = promDs;
-            expr = "partition_used_bytes{mount=\"/persistent\"} / partition_size_bytes{mount=\"/persistent\"} * 100";
+            expr = "(node_filesystem_size_bytes{mountpoint=\"/persistent\"} - node_filesystem_avail_bytes{mountpoint=\"/persistent\"}) / node_filesystem_size_bytes{mountpoint=\"/persistent\"} * 100";
            legendFormat = "/persistent";
            refId = "B";
          }
          {
            datasource = promDs;
-            expr = "partition_used_bytes{mount=\"/nix\"} / partition_size_bytes{mount=\"/nix\"} * 100";
+            expr = "(node_filesystem_size_bytes{mountpoint=\"/nix\"} - node_filesystem_avail_bytes{mountpoint=\"/nix\"}) / node_filesystem_size_bytes{mountpoint=\"/nix\"} * 100";
            legendFormat = "/nix";
            refId = "C";
          }
--- a/services/grafana/default.nix
+++ b/services/grafana/default.nix
@@ -5,8 +5,6 @@
    ./dashboard.nix
    ./exporters.nix
    ./jellyfin-annotations.nix
-    ./disk-usage-collector.nix
-    ./llama-cpp-annotations.nix
    ./zfs-scrub-annotations.nix
  ];
 }
--- a/services/grafana/disk-usage-collector.nix
+++ b/services/grafana/disk-usage-collector.nix
@@ -1,38 +0,0 @@
-{
-  config,
-  pkgs,
-  lib,
-  ...
-}:
-let
-  textfileDir = "/var/lib/prometheus-node-exporter-textfiles";
-
-  diskUsageCollector = pkgs.writeShellApplication {
-    name = "disk-usage-collector";
-    runtimeInputs = with pkgs; [
-      coreutils
-      gawk
-      config.boot.zfs.package
-      util-linux # for mountpoint
-    ];
-    text = builtins.readFile ./disk-usage-collector.sh;
-  };
-in
-lib.mkIf config.services.grafana.enable {
-  systemd.services.disk-usage-collector = {
-    description = "Collect ZFS pool and partition usage metrics for Prometheus";
-    serviceConfig = {
-      Type = "oneshot";
-      ExecStart = lib.getExe diskUsageCollector;
-    };
-    environment.TEXTFILE = "${textfileDir}/disk-usage.prom";
-  };
-
-  systemd.timers.disk-usage-collector = {
-    wantedBy = [ "timers.target" ];
-    timerConfig = {
-      OnCalendar = "minutely";
-      RandomizedDelaySec = "10s";
-    };
-  };
-}
--- a/services/grafana/disk-usage-collector.sh
+++ b/services/grafana/disk-usage-collector.sh
@@ -1,44 +0,0 @@
-#!/usr/bin/env bash
-# Collects ZFS pool utilization and boot partition usage for Prometheus textfile collector
-set -euo pipefail
-
-TEXTFILE="${TEXTFILE:?TEXTFILE env required}"
-TMP="${TEXTFILE}.$$"
-
-{
-  echo '# HELP zpool_size_bytes Total size of ZFS pool in bytes'
-  echo '# TYPE zpool_size_bytes gauge'
-  echo '# HELP zpool_used_bytes Used space in ZFS pool in bytes'
-  echo '# TYPE zpool_used_bytes gauge'
-  echo '# HELP zpool_free_bytes Free space in ZFS pool in bytes'
-  echo '# TYPE zpool_free_bytes gauge'
-
-  # -Hp: scripting mode, parseable, bytes
-  zpool list -Hp -o name,size,alloc,free | while IFS=$'\t' read -r name size alloc free; do
-    echo "zpool_size_bytes{pool=\"${name}\"} ${size}"
-    echo "zpool_used_bytes{pool=\"${name}\"} ${alloc}"
-    echo "zpool_free_bytes{pool=\"${name}\"} ${free}"
-  done
-
-  echo '# HELP partition_size_bytes Total size of partition in bytes'
-  echo '# TYPE partition_size_bytes gauge'
-  echo '# HELP partition_used_bytes Used space on partition in bytes'
-  echo '# TYPE partition_used_bytes gauge'
-  echo '# HELP partition_free_bytes Free space on partition in bytes'
-  echo '# TYPE partition_free_bytes gauge'
-
-  # Boot drive partitions: /boot (ESP), /persistent, /nix
-  # Use df with 1K blocks and convert to bytes
-  for mount in /boot /persistent /nix; do
-    if mountpoint -q "$mount" 2>/dev/null; then
-      read -r size used avail _ <<< "$(df -k --output=size,used,avail "$mount" | tail -1)"
-      size_b=$((size * 1024))
-      used_b=$((used * 1024))
-      avail_b=$((avail * 1024))
-      echo "partition_size_bytes{mount=\"${mount}\"} ${size_b}"
-      echo "partition_used_bytes{mount=\"${mount}\"} ${used_b}"
-      echo "partition_free_bytes{mount=\"${mount}\"} ${avail_b}"
-    fi
-  done
-} > "$TMP"
-mv "$TMP" "$TEXTFILE"
--- a/services/grafana/grafana.nix
+++ b/services/grafana/grafana.nix
@@ -12,6 +12,11 @@
    (lib.serviceFilePerms "grafana" [
      "Z ${service_configs.grafana.dir} 0700 grafana grafana"
    ])
+    (lib.mkCaddyReverseProxy {
+      domain = service_configs.grafana.domain;
+      port = service_configs.ports.private.grafana.port;
+      auth = true;
+    })
  ];

  services.grafana = {
@@ -85,11 +90,6 @@
    };
  };

-  services.caddy.virtualHosts."${service_configs.grafana.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${toString service_configs.ports.private.grafana.port}
-  '';
-
  services.postgresql = {
    ensureDatabases = [ "grafana" ];
    ensureUsers = [
--- a/services/grafana/jellyfin-annotations.nix
+++ b/services/grafana/jellyfin-annotations.nix
@@ -1,40 +1,18 @@
 {
  config,
-  pkgs,
  service_configs,
  lib,
  ...
 }:
-lib.mkIf (config.services.grafana.enable && config.services.jellyfin.enable) {
-  systemd.services.jellyfin-annotations = {
+lib.mkIf (config.services.grafana.enable && config.services.jellyfin.enable) (
+  lib.mkGrafanaAnnotationService {
+    name = "jellyfin";
    description = "Jellyfin stream annotation service for Grafana";
-    after = [
-      "network.target"
-      "grafana.service"
-    ];
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      ExecStart = "${pkgs.python3}/bin/python3 ${./jellyfin-annotations.py}";
-      Restart = "always";
-      RestartSec = "10s";
-      LoadCredential = "jellyfin-api-key:${config.age.secrets.jellyfin-api-key.path}";
-      DynamicUser = true;
-      StateDirectory = "jellyfin-annotations";
-      NoNewPrivileges = true;
-      ProtectSystem = "strict";
-      ProtectHome = true;
-      PrivateTmp = true;
-      RestrictAddressFamilies = [
-        "AF_INET"
-        "AF_INET6"
-      ];
-      MemoryDenyWriteExecute = true;
-    };
+    script = ./jellyfin-annotations.py;
    environment = {
      JELLYFIN_URL = "http://127.0.0.1:${toString service_configs.ports.private.jellyfin.port}";
-      GRAFANA_URL = "http://127.0.0.1:${toString service_configs.ports.private.grafana.port}";
-      STATE_FILE = "/var/lib/jellyfin-annotations/state.json";
      POLL_INTERVAL = "30";
    };
-  };
-}
+    loadCredential = "jellyfin-api-key:${config.age.secrets.jellyfin-api-key.path}";
+  }
+)
--- a/services/grafana/llama-cpp-annotations.nix
+++ b/services/grafana/llama-cpp-annotations.nix
@@ -1,39 +0,0 @@
-{
-  config,
-  pkgs,
-  service_configs,
-  lib,
-  ...
-}:
-lib.mkIf (config.services.grafana.enable && config.services.llama-cpp.enable) {
-  systemd.services.llama-cpp-annotations = {
-    description = "LLM request annotation service for Grafana";
-    after = [
-      "grafana.service"
-      "llama-cpp.service"
-    ];
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      ExecStart = "${pkgs.python3}/bin/python3 ${./llama-cpp-annotations.py}";
-      Restart = "always";
-      RestartSec = "10s";
-      DynamicUser = true;
-      StateDirectory = "llama-cpp-annotations";
-      NoNewPrivileges = true;
-      ProtectSystem = "strict";
-      ProtectHome = true;
-      PrivateTmp = true;
-      RestrictAddressFamilies = [
-        "AF_INET"
-        "AF_INET6"
-      ];
-      MemoryDenyWriteExecute = true;
-    };
-    environment = {
-      GRAFANA_URL = "http://127.0.0.1:${toString service_configs.ports.private.grafana.port}";
-      STATE_FILE = "/var/lib/llama-cpp-annotations/state.json";
-      POLL_INTERVAL = "5";
-      CPU_THRESHOLD = "50";
-    };
-  };
-}
--- a/services/grafana/llama-cpp-annotations.py
+++ b/services/grafana/llama-cpp-annotations.py
@@ -1,155 +0,0 @@
-#!/usr/bin/env python3
-"""
-Grafana annotation service for llama-cpp inference requests.
-
-Monitors llama-server CPU usage via /proc. Creates a Grafana annotation
-when inference starts (CPU spikes), closes it when inference ends.
-"""
-
-import glob
-import json
-import os
-import sys
-import time
-import urllib.request
-
-GRAFANA_URL = os.environ.get("GRAFANA_URL", "http://127.0.0.1:3000")
-STATE_FILE = os.environ.get("STATE_FILE", "/var/lib/llama-cpp-annotations/state.json")
-POLL_INTERVAL = int(os.environ.get("POLL_INTERVAL", "5"))
-CPU_THRESHOLD = float(os.environ.get("CPU_THRESHOLD", "50"))
-
-
-def find_llama_pid():
-    for path in glob.glob("/proc/[0-9]*/comm"):
-        try:
-            with open(path) as f:
-                if f.read().strip() == "llama-server":
-                    return int(path.split("/")[2])
-        except (OSError, ValueError):
-            continue
-    return None
-
-
-def get_cpu_times(pid):
-    try:
-        with open(f"/proc/{pid}/stat") as f:
-            fields = f.read().split(")")[-1].split()
-            return int(fields[11]) + int(fields[12])
-    except (OSError, IndexError, ValueError):
-        return None
-
-
-def http_json(method, url, body=None):
-    data = json.dumps(body).encode() if body is not None else None
-    req = urllib.request.Request(
-        url,
-        data=data,
-        headers={"Content-Type": "application/json", "Accept": "application/json"},
-        method=method,
-    )
-    with urllib.request.urlopen(req, timeout=5) as resp:
-        return json.loads(resp.read())
-
-
-def load_state():
-    try:
-        with open(STATE_FILE) as f:
-            return json.load(f)
-    except (FileNotFoundError, json.JSONDecodeError):
-        return {}
-
-
-def save_state(state):
-    os.makedirs(os.path.dirname(STATE_FILE), exist_ok=True)
-    tmp = STATE_FILE + ".tmp"
-    with open(tmp, "w") as f:
-        json.dump(state, f)
-    os.replace(tmp, STATE_FILE)
-
-
-def grafana_post(text, start_ms):
-    try:
-        result = http_json(
-            "POST",
-            f"{GRAFANA_URL}/api/annotations",
-            {"time": start_ms, "text": text, "tags": ["llama-cpp"]},
-        )
-        return result.get("id")
-    except Exception as e:
-        print(f"Error posting annotation: {e}", file=sys.stderr)
-        return None
-
-
-def grafana_close(grafana_id, end_ms, text=None):
-    try:
-        body = {"timeEnd": end_ms}
-        if text is not None:
-            body["text"] = text
-        http_json(
-            "PATCH",
-            f"{GRAFANA_URL}/api/annotations/{grafana_id}",
-            body,
-        )
-    except Exception as e:
-        print(f"Error closing annotation {grafana_id}: {e}", file=sys.stderr)
-
-
-def main():
-    state = load_state()
-    prev_ticks = None
-    prev_time = None
-    hz = os.sysconf("SC_CLK_TCK")
-
-    while True:
-        now_ms = int(time.time() * 1000)
-        pid = find_llama_pid()
-
-        if pid is None:
-            prev_ticks = None
-            prev_time = None
-            time.sleep(POLL_INTERVAL)
-            continue
-
-        ticks = get_cpu_times(pid)
-        now = time.monotonic()
-
-        if ticks is None or prev_ticks is None or prev_time is None:
-            prev_ticks = ticks
-            prev_time = now
-            time.sleep(POLL_INTERVAL)
-            continue
-
-        dt = now - prev_time
-        if dt <= 0:
-            prev_ticks = ticks
-            prev_time = now
-            time.sleep(POLL_INTERVAL)
-            continue
-
-        cpu_pct = ((ticks - prev_ticks) / hz) / dt * 100
-        prev_ticks = ticks
-        prev_time = now
-
-        busy = cpu_pct > CPU_THRESHOLD
-
-        if busy and "active" not in state:
-            grafana_id = grafana_post("LLM request", now_ms)
-            if grafana_id is not None:
-                state["active"] = {
-                    "grafana_id": grafana_id,
-                    "start_ms": now_ms,
-                }
-                save_state(state)
-
-        elif not busy and "active" in state:
-            info = state.pop("active")
-            duration_s = (now_ms - info["start_ms"]) / 1000
-            text = f"LLM request ({duration_s:.1f}s)"
-            grafana_close(info["grafana_id"], now_ms, text)
-            save_state(state)
-
-        time.sleep(POLL_INTERVAL)
-
-
-if __name__ == "__main__":
-    main()
--- a/services/grafana/prometheus.nix
+++ b/services/grafana/prometheus.nix
@@ -44,6 +44,12 @@ in
        listenAddress = "127.0.0.1";
        apcupsdAddress = "127.0.0.1:3551";
      };
+
+      zfs = {
+        enable = true;
+        port = service_configs.ports.private.prometheus_zfs.port;
+        listenAddress = "127.0.0.1";
+      };
    };

    scrapeConfigs = [
@@ -89,6 +95,12 @@ in
          { targets = [ "127.0.0.1:${toString service_configs.ports.private.igpu_exporter.port}" ]; }
        ];
      }
+      {
+        job_name = "zfs";
+        static_configs = [
+          { targets = [ "127.0.0.1:${toString service_configs.ports.private.prometheus_zfs.port}" ]; }
+        ];
+      }
    ];
  };

--- a/services/immich.nix
+++ b/services/immich.nix
@@ -16,6 +16,15 @@
    (lib.serviceFilePerms "immich-server" [
      "Z ${config.services.immich.mediaLocation} 0770 ${config.services.immich.user} ${config.services.immich.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "immich";
+      port = service_configs.ports.private.immich.port;
+    })
+    (lib.mkFail2banJail {
+      name = "immich";
+      unitName = "immich-server.service";
+      failregex = "^.*Failed login attempt for user .* from ip address <HOST>.*$";
+    })
  ];

  services.immich = {
@@ -29,10 +38,6 @@
    };
  };

-  services.caddy.virtualHosts."immich.${service_configs.https.domain}".extraConfig = ''
-    reverse_proxy :${builtins.toString config.services.immich.port}
-  '';
-
  environment.systemPackages = with pkgs; [
    immich-go
  ];
@@ -42,18 +47,4 @@
    "render"
  ];

-  # Protect Immich login from brute force attacks
-  services.fail2ban.jails.immich = {
-    enabled = true;
-    settings = {
-      backend = "systemd";
-      port = "http,https";
-      # defaults: maxretry=5, findtime=10m, bantime=10m
-    };
-    filter.Definition = {
-      failregex = "^.*Failed login attempt for user .* from ip address <HOST>.*$";
-      ignoreregex = "";
-      journalmatch = "_SYSTEMD_UNIT=immich-server.service";
-    };
-  };
 }
--- a/services/llama-cpp.nix
+++ b/services/llama-cpp.nix
@@ -13,6 +13,13 @@ let
  modelAlias = lib.removeSuffix ".gguf" (baseNameOf modelUrl);
 in
 {
+  imports = [
+    (lib.mkCaddyReverseProxy {
+      subdomain = "llm";
+      port = service_configs.ports.private.llama_cpp.port;
+    })
+  ];
+
  services.llama-cpp = {
    enable = true;
    model = toString (
@@ -94,10 +101,4 @@ in
    + " ${utils.escapeSystemdExecArgs cfg.extraFlags}"
  );

-  # Auth handled by llama-cpp --api-key-file (Bearer token).
-  # No caddy_auth — the API key is the auth layer, and caddy_auth's basic
-  # auth would block Bearer-only clients like oh-my-pi.
-  services.caddy.virtualHosts."llm.${service_configs.https.domain}".extraConfig = ''
-    reverse_proxy :${toString config.services.llama-cpp.port}
-  '';
 }
--- a/services/matrix/matrix.nix
+++ b/services/matrix/matrix.nix
@@ -12,6 +12,10 @@
    (lib.serviceFilePerms "continuwuity" [
      "Z /var/lib/private/continuwuity 0770 ${config.services.matrix-continuwuity.user} ${config.services.matrix-continuwuity.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      domain = service_configs.matrix.domain;
+      port = service_configs.ports.private.matrix.port;
+    })
  ];

  services.matrix-continuwuity = {
@@ -53,10 +57,6 @@
    respond /.well-known/matrix/client `{"m.server":{"base_url":"https://${service_configs.matrix.domain}"},"m.homeserver":{"base_url":"https://${service_configs.matrix.domain}"},"org.matrix.msc3575.proxy":{"base_url":"https://${config.services.matrix-continuwuity.settings.global.server_name}"},"org.matrix.msc4143.rtc_foci":[{"type":"livekit","livekit_service_url":"https://${service_configs.livekit.domain}"}]}`
  '';

-  services.caddy.virtualHosts."${service_configs.matrix.domain}".extraConfig = ''
-    reverse_proxy :${builtins.toString service_configs.ports.private.matrix.port}
-  '';
-
  # Exact duplicate for federation port
  services.caddy.virtualHosts."${service_configs.matrix.domain}:${builtins.toString service_configs.ports.public.matrix_federation.port}".extraConfig =
    config.services.caddy.virtualHosts."${service_configs.matrix.domain}".extraConfig;
--- a/services/ntfy/ntfy.nix
+++ b/services/ntfy/ntfy.nix
@@ -12,6 +12,10 @@
    (lib.serviceFilePerms "ntfy-sh" [
      "Z /var/lib/private/ntfy-sh 0700 ${config.services.ntfy-sh.user} ${config.services.ntfy-sh.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      domain = service_configs.ntfy.domain;
+      port = service_configs.ports.private.ntfy.port;
+    })
  ];

  services.ntfy-sh = {
@@ -27,8 +31,4 @@
    };
  };

-  services.caddy.virtualHosts."${service_configs.ntfy.domain}".extraConfig = ''
-    reverse_proxy :${builtins.toString service_configs.ports.private.ntfy.port}
-  '';
-
 }
--- a/services/qbittorrent.nix
+++ b/services/qbittorrent.nix
@@ -27,6 +27,12 @@ in
      "z ${config.services.qbittorrent.serverConfig.Preferences.Downloads.TempPath} 0700 ${config.services.qbittorrent.user} ${config.services.qbittorrent.group}"
      "Z ${config.services.qbittorrent.profileDir} 0700 ${config.services.qbittorrent.user} ${config.services.qbittorrent.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "torrent";
+      port = service_configs.ports.private.torrent.port;
+      auth = true;
+      vpn = true;
+    })
  ];

  services.qbittorrent = {
@@ -156,11 +162,6 @@ in
    _: path: "d ${path} 0770 ${config.services.qbittorrent.user} ${service_configs.media_group} -"
  ) service_configs.torrent.categories;

-  services.caddy.virtualHosts."torrent.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy ${config.vpnNamespaces.wg.namespaceAddress}:${builtins.toString config.services.qbittorrent.webuiPort}
-  '';
-
  users.users.${config.services.qbittorrent.user}.extraGroups = [
    service_configs.media_group
  ];
--- a/services/soulseek.nix
+++ b/services/soulseek.nix
@@ -19,6 +19,10 @@
      "Z ${service_configs.slskd.downloads} 0750 ${config.services.slskd.user} music"
      "Z ${service_configs.slskd.incomplete} 0750 ${config.services.slskd.user} music"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "soulseek";
+      port = service_configs.ports.private.soulseek_web.port;
+    })
  ];

  users.groups."music" = { };
@@ -58,11 +62,6 @@
  users.users.${config.services.jellyfin.user}.extraGroups = [ "music" ];
  users.users.${username}.extraGroups = [ "music" ];

-  # doesn't work with auth????
-  services.caddy.virtualHosts."soulseek.${service_configs.https.domain}".extraConfig = ''
-    reverse_proxy :${builtins.toString config.services.slskd.settings.web.port}
-  '';
-
  networking.firewall.allowedTCPPorts = [
    service_configs.ports.public.soulseek_listen.port
  ];
--- a/services/syncthing.nix
+++ b/services/syncthing.nix
@@ -17,6 +17,11 @@
      "Z ${service_configs.syncthing.signalBackupDir} 0750 ${config.services.syncthing.user} ${config.services.syncthing.group}"
      "Z ${service_configs.syncthing.grayjayBackupDir} 0750 ${config.services.syncthing.user} ${config.services.syncthing.group}"
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "syncthing";
+      port = service_configs.ports.private.syncthing_gui.port;
+      auth = true;
+    })
  ];

  services.syncthing = {
@@ -49,9 +54,4 @@
    ];
  };

-  services.caddy.virtualHosts."syncthing.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${toString service_configs.ports.private.syncthing_gui.port}
-  '';
-
 }
--- a/services/trilium.nix
+++ b/services/trilium.nix
@@ -10,6 +10,11 @@
    (lib.serviceMountWithZpool "trilium-server" service_configs.zpool_ssds [
      (service_configs.services_dir + "/trilium")
    ])
+    (lib.mkCaddyReverseProxy {
+      subdomain = "notes";
+      port = service_configs.ports.private.trilium.port;
+      auth = true;
+    })
  ];

  services.trilium-server = {
@@ -19,8 +24,4 @@
    dataDir = service_configs.trilium.dataDir;
  };

-  services.caddy.virtualHosts."notes.${service_configs.https.domain}".extraConfig = ''
-    import ${config.age.secrets.caddy_auth.path}
-    reverse_proxy :${toString service_configs.ports.private.trilium.port}
-  '';
 }
--- a/tests/llama-cpp-annotations.nix
+++ b/tests/llama-cpp-annotations.nix
@@ -1,132 +0,0 @@
-{
-  pkgs,
-  ...
-}:
-let
-  mockGrafana = ./mock-grafana-server.py;
-  script = ../services/grafana/llama-cpp-annotations.py;
-  python = pkgs.python3;
-
-  mockLlamaProcess = ./mock-llama-server-proc.py;
-in
-pkgs.testers.runNixOSTest {
-  name = "llama-cpp-annotations";
-
-  nodes.machine =
-    { pkgs, ... }:
-    {
-      environment.systemPackages = [
-        pkgs.python3
-        pkgs.curl
-        pkgs.procps
-      ];
-    };
-
-  testScript = ''
-    import json
-    import time
-
-    GRAFANA_PORT = 13000
-    ANNOTS_FILE = "/tmp/annotations.json"
-    LLAMA_STATE = "/tmp/llama-state.txt"
-    STATE_FILE = "/tmp/llama-annot-state.json"
-    PYTHON = "${python}/bin/python3"
-    MOCK_GRAFANA = "${mockGrafana}"
-    MOCK_LLAMA = "${mockLlamaProcess}"
-    SCRIPT = "${script}"
-
-    def read_annotations():
-        out = machine.succeed(f"cat {ANNOTS_FILE} 2>/dev/null || echo '[]'")
-        return json.loads(out.strip())
-
-    def set_busy():
-        machine.succeed(f"echo busy > {LLAMA_STATE}")
-
-    def set_idle():
-        machine.succeed(f"echo idle > {LLAMA_STATE}")
-
-    start_all()
-    machine.wait_for_unit("multi-user.target")
-
-    with subtest("Start mock services"):
-        machine.succeed(f"echo '[]' > {ANNOTS_FILE}")
-        machine.succeed(
-            f"systemd-run --unit=mock-grafana {PYTHON} {MOCK_GRAFANA} {GRAFANA_PORT} {ANNOTS_FILE}"
-        )
-        machine.succeed(
-            f"systemd-run --unit=mock-llama {PYTHON} {MOCK_LLAMA} {LLAMA_STATE}"
-        )
-        machine.wait_until_succeeds(
-            f"curl -sf http://127.0.0.1:{GRAFANA_PORT}/api/annotations -X POST "
-            f"-H 'Content-Type: application/json' -d '{{\"text\":\"ping\",\"tags\":[]}}' | grep -q id",
-            timeout=10,
-        )
-        machine.wait_until_succeeds(
-            "pgrep -x llama-server",
-            timeout=10,
-        )
-        machine.succeed(f"echo '[]' > {ANNOTS_FILE}")
-
-    with subtest("Start annotation service"):
-        machine.succeed(
-            f"systemd-run --unit=llama-annot "
-            f"--setenv=GRAFANA_URL=http://127.0.0.1:{GRAFANA_PORT} "
-            f"--setenv=STATE_FILE={STATE_FILE} "
-            f"--setenv=POLL_INTERVAL=2 "
-            f"--setenv=CPU_THRESHOLD=10 "
-            f"{PYTHON} {SCRIPT}"
-        )
-        time.sleep(5)
-
-    with subtest("No annotations when idle"):
-        annots = read_annotations()
-        assert annots == [], f"Expected no annotations, got: {annots}"
-
-    with subtest("Annotation created when llama-server becomes busy"):
-        set_busy()
-        machine.wait_until_succeeds(
-            f"cat {ANNOTS_FILE} | {PYTHON} -c "
-            f"\"import sys,json; a=json.load(sys.stdin); exit(0 if a else 1)\"",
-            timeout=20,
-        )
-        annots = read_annotations()
-        assert len(annots) == 1, f"Expected 1 annotation, got: {annots}"
-        assert "llama-cpp" in annots[0].get("tags", []), f"Missing tag: {annots[0]}"
-        assert "LLM request" in annots[0]["text"], f"Missing text: {annots[0]['text']}"
-        assert "timeEnd" not in annots[0], f"timeEnd should not be set: {annots[0]}"
-
-    with subtest("Annotation closed when llama-server becomes idle"):
-        set_idle()
-        machine.wait_until_succeeds(
-            f"cat {ANNOTS_FILE} | {PYTHON} -c "
-            f"\"import sys,json; a=json.load(sys.stdin); exit(0 if a and 'timeEnd' in a[0] else 1)\"",
-            timeout=20,
-        )
-        annots = read_annotations()
-        assert len(annots) == 1, f"Expected 1, got: {annots}"
-        assert "timeEnd" in annots[0], f"timeEnd missing: {annots[0]}"
-        assert annots[0]["timeEnd"] > annots[0]["time"], "timeEnd should be after time"
-        assert "s)" in annots[0].get("text", ""), f"Duration missing: {annots[0]}"
-
-    with subtest("State survives restart"):
-        set_busy()
-        machine.wait_until_succeeds(
-            f"cat {ANNOTS_FILE} | {PYTHON} -c "
-            f"\"import sys,json; a=json.load(sys.stdin); exit(0 if len(a)==2 else 1)\"",
-            timeout=20,
-        )
-        machine.succeed("systemctl stop llama-annot || true")
-        time.sleep(1)
-        machine.succeed(
-            f"systemd-run --unit=llama-annot-2 "
-            f"--setenv=GRAFANA_URL=http://127.0.0.1:{GRAFANA_PORT} "
-            f"--setenv=STATE_FILE={STATE_FILE} "
-            f"--setenv=POLL_INTERVAL=2 "
-            f"--setenv=CPU_THRESHOLD=10 "
-            f"{PYTHON} {SCRIPT}"
-        )
-        time.sleep(6)
-        annots = read_annotations()
-        assert len(annots) == 2, f"Restart should not duplicate, got: {annots}"
-  '';
-}
--- a/tests/mock-llama-server-proc.py
+++ b/tests/mock-llama-server-proc.py
@@ -1,42 +0,0 @@
-#!/usr/bin/env python3
-"""
-Mock llama-server process for NixOS VM tests.
-
-Sets /proc/self/comm to "llama-server" via prctl so that monitoring scripts
-(llama-cpp-annotations, llama-cpp-xmrig-pause) can discover this process
-the same way they discover the real one.
-
-Usage: python3 mock-llama-server-proc.py <state-file>
-
-The state file controls behavior:
-  "busy"  -> burn CPU in a tight loop (simulates prompt processing / inference)
-  "idle"  -> sleep (simulates waiting for requests)
-"""
-
-import ctypes
-import ctypes.util
-import sys
-import time
-
-STATE_FILE = sys.argv[1]
-
-# PR_SET_NAME = 15, sets /proc/self/comm
-libc = ctypes.CDLL(ctypes.util.find_library("c"), use_errno=True)
-libc.prctl(15, b"llama-server", 0, 0, 0)
-
-with open(STATE_FILE, "w") as f:
-    f.write("idle")
-
-while True:
-    try:
-        with open(STATE_FILE) as f:
-            state = f.read().strip()
-    except Exception:
-        state = "idle"
-
-    if state == "busy":
-        end = time.monotonic() + 0.1
-        while time.monotonic() < end:
-            _ = sum(range(10000))
-    else:
-        time.sleep(0.5)
--- a/tests/tests.nix
+++ b/tests/tests.nix
@@ -28,9 +28,6 @@ in
  # zfs scrub annotations test
  zfsScrubAnnotationsTest = handleTest ./zfs-scrub-annotations.nix;

-  # llama-cpp tests
-  llamaCppAnnotationsTest = handleTest ./llama-cpp-annotations.nix;
-
  # xmrig auto-pause test
  xmrigAutoPauseTest = handleTest ./xmrig-auto-pause.nix;
  # ntfy alerts test
Author	SHA1	Message	Date
Simon Gardling	ce1c335230	caddy: wildcard TLS via DNS-01 challenge + ddns-updater for Njalla Some checks failed Build and Deploy / deploy (push) Failing after 31m3s Build Caddy with the caddy-dns/njalla plugin to enable DNS-01 ACME challenges. This issues a single wildcard certificate for *.sigkill.computer instead of per-subdomain certificates, reducing Let's Encrypt API calls and certificate management overhead. Add ddns-updater service (nixpkgs services.ddns-updater) configured with Njalla provider to automatically update DNS records when the server's public IP changes.	2026-04-09 19:54:57 -04:00
Simon Gardling	e9ce1ce0a2	grafana: replace llama-cpp-annotations daemon with prometheus query	2026-04-09 19:54:57 -04:00
Simon Gardling	a3a6700106	grafana: replace disk-usage-collector with prometheus-zfs-exporter The custom disk-usage-collector shell script + minutely timer is replaced by prometheus-zfs-exporter (pdf/zfs_exporter, packaged in nixpkgs as services.prometheus.exporters.zfs). The exporter provides pool capacity metrics (allocated/free/size) natively. Partition metrics (/boot, /persistent, /nix) now use node_exporter's built-in filesystem collector (node_filesystem_*_bytes) which already runs and collects these metrics. Also fixes a latent race condition in serviceMountWithZpool: the -mounts service now orders after zfs-mount.service (which runs 'zfs mount -a'), not just after pool import. Without this, the mount check could run before datasets are actually mounted.	2026-04-09 19:54:57 -04:00
Simon Gardling	75319256f3	lib: add mkCaddyReverseProxy, mkFail2banJail, mkGrafanaAnnotationService, extractArrApiKey	2026-04-09 19:54:57 -04:00