fix(mx): point nextcloud bot at the fast model

halo's llama-server now runs in router mode where the model field selects
a preset (coder/fast/bge-m3); the old "halo-8000" name is no longer valid.
Use the fast MoE model for the Talk bot's responses.

systems/x86_64-linux/mx/nextcloud-opencode-bot/default.nix

@@ -7,7 +7,7 @@
     nextcloudUrl = "https://nc.hoyer.xyz";
     botSecretFile = config.sops.secrets."nextcloud-opencode-bot/secret".path;
     modelBaseUrl = "http://halo.hoyer.tail:8000/v1";
-    model = "halo-8000";
+    model = "fast";
     botName = "Halo";
     timeout = 200;
     allowedUsers = [ ];