hosts/m3-hermes/configuration.nix

@@ -13,6 +13,18 @@
   networking.hostName = "m3-hermes";
   networking.hostId = "a1b2c3d4"; # TODO: Generate unique hostId
   networking.networkmanager.enable = true;
+
+  # Matrix homeserver pin: DNS on this host resolves exclusively via the
+  # Netbird-managed resolver (see /etc/resolv.conf → wt0). When the Netbird
+  # nameserver group is unreachable, matrix.m3ta.dev fails to resolve and the
+  # gateway cannot log in (observed 2026-08-16). Pinning the public IP of
+  # m3-atlas (TLS termination for matrix.m3ta.dev) makes the Matrix connection
+  # independent of Netbird DNS health. Update here if the m3-atlas public IP
+  # ever changes.
+  networking.hosts = {
+    "152.53.85.162" = ["matrix.m3ta.dev"];
+  };
+
   time.timeZone = "Europe/Berlin";
   i18n.defaultLocale = "en_US.UTF-8";
 

hosts/m3-hermes/services/hermes-agent.nix

@@ -104,6 +104,15 @@ in {
       GIT_COMMITTER_EMAIL = "m3ta-chiron@agentmail.to";
       GIT_INIT_DEFAULT_BRANCH = "master";
 
+      # ── Matrix: stable device (Fix 0, root cause of ghost-device churn) ──
+      # Every gateway restart with password login creates a NEW device on the
+      # homeserver when MATRIX_DEVICE_ID is unset. The matching secret
+      # MATRIX_ACCESS_TOKEN lives in agenix (secrets/hermes-env.age). The token
+      # also keeps Matrix in the gateway's reconnect queue: without it, a
+      # failed startup (e.g. transient DNS outage) permanently drops the
+      # platform ("no bot credential on queued config").
+      MATRIX_DEVICE_ID = "HERMES01";
+
       # ── API Server (OpenAI-compatible, for Hermes Desktop App) ─────────
       # Accessible via Netbird mesh VPN — not exposed to the public internet.
       # Bind to 0.0.0.0 so the Netbird interface can reach it.