Serve the frontend on the bare domain instead of app.<domain>

Only drb.cusano.net and api.drb.cusano.net have public A records, so the
app.<domain> vhost had no cert to present and the bare domain — the record
that actually exists — matched no site at all, producing
ERR_SSL_PROTOCOL_ERROR in the browser.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docker-compose.prod.yml

@@ -12,9 +12,14 @@ services:
     restart: always
     ports: !reset []   # Remove the dev 1883:1883 mapping — internal only
 
+  # !override, not a plain list: compose MERGES `ports` by appending, so a plain
+  # list leaves the base file's "8888:8000" in place alongside this one. The
+  # container then tries to bind 8888 twice — 0.0.0.0 and 127.0.0.1 — and the
+  # second bind fails with "address already in use". It also silently defeated
+  # the whole point of this override, publishing the port on every interface.
   c2-core:
     restart: always
-    ports:
+    ports: !override
       - "127.0.0.1:8888:8000"  # Caddy proxies, not exposed publicly
 
   discord-bot:
@@ -22,5 +27,5 @@ services:
 
   frontend:
     restart: always
-    ports:
+    ports: !override
       - "127.0.0.1:3000:3000"  # Caddy proxies, not exposed publicly

drb-c2-core/app/internal/mqtt_handler.py

@@ -1,6 +1,6 @@
 import asyncio
 import json
-from datetime import datetime, timezone
+from datetime import datetime, timezone, timedelta
 from typing import Optional
 import paho.mqtt.client as mqtt
 from app.config import settings
@@ -94,6 +94,11 @@ class MQTTHandler:
                 "last_seen": now.isoformat(),
                 "assigned_system_id": None,
                 "approval_status": "pending",
+                "node_type": payload.get("node_type", "fixed"),
+                "enforce_override_timeout": payload.get("enforce_override_timeout", True),
+                "is_overridden": False,
+                "override_system_id": None,
+                "override_timeout_at": None,
             }
             await fstore.doc_set("nodes", node_id, doc, merge=False)
             logger.info(f"New node registered: {node_id} — pending admin approval.")
@@ -111,6 +116,37 @@ class MQTTHandler:
                 elif existing.get("approval_status") == "approved":
                     # Approved but not yet configured — restore reachable status after reboot
                     updates["status"] = "unconfigured"
+            
+            node_type = payload.get("node_type") or existing.get("node_type") or "fixed"
+            enforce_timeout = payload.get("enforce_override_timeout")
+            if enforce_timeout is None:
+                enforce_timeout = existing.get("enforce_override_timeout", True)
+            
+            updates["node_type"] = node_type
+            updates["enforce_override_timeout"] = enforce_timeout
+            
+            is_overridden = payload.get("is_overridden", False)
+            override_system_id = payload.get("override_system_id")
+            
+            if node_type == "portable":
+                updates["is_overridden"] = False
+                updates["override_system_id"] = None
+                updates["override_timeout_at"] = None
+            else:
+                updates["is_overridden"] = is_overridden
+                updates["override_system_id"] = override_system_id
+                
+                if is_overridden:
+                    existing_timeout = existing.get("override_timeout_at")
+                    existing_override_id = existing.get("override_system_id")
+                    if enforce_timeout:
+                        if not existing_timeout or existing_override_id != override_system_id:
+                            updates["override_timeout_at"] = (now + timedelta(hours=24)).isoformat()
+                    else:
+                        updates["override_timeout_at"] = None
+                else:
+                    updates["override_timeout_at"] = None
+
             await fstore.doc_update("nodes", node_id, updates)
 
         # NOTE: discord_connected in checkins is informational only — do NOT release the

drb-c2-core/app/internal/node_sweeper.py

@@ -55,3 +55,35 @@ async def _sweep():
             logger.info(f"Node {node_id} marked offline (last seen: {last_seen.isoformat()})")
             from app.routers.tokens import release_token
             await release_token(node_id)
+            continue
+
+        # Check for expired system overrides (only for fixed nodes with timeout enforced)
+        override_timeout_raw = node.get("override_timeout_at")
+        enforce_timeout = node.get("enforce_override_timeout", True)
+        node_type = node.get("node_type", "fixed")
+
+        if override_timeout_raw and enforce_timeout and node_type != "portable":
+            if isinstance(override_timeout_raw, str):
+                override_timeout = datetime.fromisoformat(override_timeout_raw)
+            else:
+                override_timeout = override_timeout_raw
+            if override_timeout.tzinfo is None:
+                override_timeout = override_timeout.replace(tzinfo=timezone.utc)
+
+            if datetime.now(timezone.utc) > override_timeout:
+                node_id = node.get("node_id")
+                assigned_system_id = node.get("assigned_system_id")
+                logger.info(f"Node {node_id} override has expired. Reverting to system {assigned_system_id}.")
+
+                # Push the original assigned config if it exists
+                if assigned_system_id:
+                    system_doc = await fstore.doc_get("systems", assigned_system_id)
+                    if system_doc:
+                        from app.internal.mqtt_handler import mqtt_handler
+                        mqtt_handler.push_config(node_id, system_doc)
+
+                await fstore.doc_update("nodes", node_id, {
+                    "is_overridden": False,
+                    "override_system_id": None,
+                    "override_timeout_at": None,
+                })

drb-c2-core/app/models.py

@@ -16,6 +16,11 @@ class NodeRecord(BaseModel):
     configured: bool = False
     last_seen: Optional[datetime] = None
     assigned_system_id: Optional[str] = None
+    node_type: str = "fixed"  # fixed or portable
+    enforce_override_timeout: bool = True
+    is_overridden: bool = False
+    override_system_id: Optional[str] = None
+    override_timeout_at: Optional[datetime] = None
 
 
 class CommandPayload(BaseModel):

drb-c2-core/app/routers/nodes.py

@@ -1,6 +1,7 @@
 import secrets
 from typing import Optional
 from fastapi import APIRouter, HTTPException, Depends, Query
+from pydantic import BaseModel
 from app.models import CommandPayload
 from app.internal import firestore as fstore
 from app.internal.mqtt_handler import mqtt_handler
@@ -126,10 +127,13 @@ async def assign_system(
     if not system:
         raise HTTPException(404, f"System '{system_id}' not found.")
 
-    # Include hardware preset in the push so the edge node applies it when
-    # generating the OP25 config. Strip it from the system doc first so it
-    # doesn't collide with SystemConfig field validation on the node side.
-    push_payload = {**system, "hardware_preset": hardware_preset}
+    # Include hardware preset, node type, and enforce timeout in the push
+    push_payload = {
+        **system, 
+        "hardware_preset": hardware_preset,
+        "node_type": node.get("node_type", "fixed"),
+        "enforce_override_timeout": node.get("enforce_override_timeout", True),
+    }
     if ppm_override is not None:
         push_payload["ppm_override"] = ppm_override
     mqtt_handler.push_config(node_id, push_payload)
@@ -145,3 +149,89 @@ async def assign_system(
     await fstore.doc_update("nodes", node_id, node_updates)
 
     return {"ok": True}
+
+
+class NodeUpdateBody(BaseModel):
+    node_type: Optional[str] = None
+    enforce_override_timeout: Optional[bool] = None
+
+
+@router.patch("/{node_id}")
+async def update_node(
+    node_id: str,
+    body: NodeUpdateBody,
+    _: dict = Depends(require_admin_token),
+):
+    node = await fstore.doc_get("nodes", node_id)
+    if not node:
+        raise HTTPException(404, f"Node '{node_id}' not found.")
+
+    updates = body.model_dump(exclude_unset=True)
+    if not updates:
+        return {"ok": True}
+
+    await fstore.doc_update("nodes", node_id, updates)
+
+    # Re-push config to apply new node settings locally
+    updated_node = await fstore.doc_get("nodes", node_id)
+    assigned_system_id = updated_node.get("assigned_system_id")
+    if assigned_system_id:
+        system = await fstore.doc_get("systems", assigned_system_id)
+        if system:
+            push_payload = {
+                **system,
+                "hardware_preset": updated_node.get("hardware_preset", "rtl-sdr-v3"),
+                "node_type": updated_node.get("node_type", "fixed"),
+                "enforce_override_timeout": updated_node.get("enforce_override_timeout", True),
+            }
+            if updated_node.get("ppm_override") is not None:
+                push_payload["ppm_override"] = updated_node["ppm_override"]
+            mqtt_handler.push_config(node_id, push_payload)
+
+    return {"ok": True}
+
+
+class AckOverrideBody(BaseModel):
+    timeout_minutes: int = 1440
+
+
+@router.post("/{node_id}/override/ack")
+async def ack_override(
+    node_id: str,
+    body: AckOverrideBody,
+    _: dict = Depends(require_service_key_or_admin),
+):
+    node = await fstore.doc_get("nodes", node_id)
+    if not node:
+        raise HTTPException(404, f"Node '{node_id}' not found.")
+
+    from datetime import datetime, timezone, timedelta
+    new_timeout = datetime.now(timezone.utc) + timedelta(minutes=body.timeout_minutes)
+    
+    await fstore.doc_update("nodes", node_id, {
+        "override_timeout_at": new_timeout.isoformat()
+    })
+    return {"ok": True, "override_timeout_at": new_timeout.isoformat()}
+
+
+@router.post("/{node_id}/override/reset")
+async def reset_override(
+    node_id: str,
+    _: dict = Depends(require_service_key_or_admin),
+):
+    node = await fstore.doc_get("nodes", node_id)
+    if not node:
+        raise HTTPException(404, f"Node '{node_id}' not found.")
+
+    assigned_system_id = node.get("assigned_system_id")
+    if assigned_system_id:
+        system = await fstore.doc_get("systems", assigned_system_id)
+        if system:
+            mqtt_handler.push_config(node_id, system)
+
+    await fstore.doc_update("nodes", node_id, {
+        "is_overridden": False,
+        "override_system_id": None,
+        "override_timeout_at": None,
+    })
+    return {"ok": True}

drb-frontend/app/nodes/[id]/page.tsx

@@ -192,6 +192,54 @@ export default function NodeDetailPage() {
         <StatusBadge status={node.status} />
       </div>
 
+      {/* Override Warning */}
+      {node.is_overridden && (
+        <div className="bg-yellow-950/40 border border-yellow-800/60 rounded-lg p-4 font-mono text-sm space-y-3">
+          <div className="flex items-center gap-2 text-yellow-400 font-semibold">
+            <span className="text-base">⚠</span>
+            <span>Local System Override Active</span>
+          </div>
+          <p className="text-gray-400 text-xs leading-relaxed">
+            This node is operating on a local system override. 
+            {node.override_timeout_at ? (
+              <> Resets automatically on: <span className="text-white font-bold">{new Date(node.override_timeout_at).toLocaleString()}</span>.</>
+            ) : (
+              <> No timeout is currently enforced (permanent override).</>
+            )}
+          </p>
+          <div className="flex gap-2">
+            {node.override_timeout_at && (
+              <button
+                onClick={async () => {
+                  try {
+                    await c2api.ackOverride(id, 1440);
+                  } catch (e) {
+                    alert("Failed to extend timer.");
+                  }
+                }}
+                className="px-3 py-1 bg-yellow-800 hover:bg-yellow-700 text-white rounded text-xs transition-colors"
+              >
+                Ack (Reset 24h Timer)
+              </button>
+            )}
+            <button
+              onClick={async () => {
+                if (confirm("Force this node to revert back to its assigned system config?")) {
+                  try {
+                    await c2api.resetOverride(id);
+                  } catch (e) {
+                    alert("Failed to reset override.");
+                  }
+                }
+              }}
+              className="px-3 py-1 bg-red-900 hover:bg-red-800 text-red-200 rounded text-xs transition-colors"
+            >
+              Force Revert Config
+            </button>
+          </div>
+        </div>
+      )}
+
       {/* Info */}
       <div className="bg-gray-900 border border-gray-800 rounded-lg divide-y divide-gray-800 font-mono text-sm">
         {[
@@ -199,6 +247,8 @@ export default function NodeDetailPage() {
           ["Location",  `${node.lat}, ${node.lon}`],
           ["Last Seen", node.last_seen ? new Date(node.last_seen).toLocaleString() : "never"],
           ["Configured", node.configured ? "Yes" : "No"],
+          ["Node Type", node.node_type ?? "fixed"],
+          ...(node.node_type !== "portable" ? [["Enforce Timeout", node.enforce_override_timeout ? "Yes" : "No"]] : []),
         ].map(([label, value]) => (
           <div key={label} className="flex justify-between px-4 py-2.5">
             <span className="text-gray-500">{label}</span>

drb-frontend/components/NodeCard.tsx

@@ -45,6 +45,18 @@ export function NodeCard({ node, system }: Props) {
             ⚠ Needs configuration
           </div>
         )}
+        {node.is_overridden && (
+          <div className="mt-3 text-xs text-yellow-500 font-mono border-t border-gray-800 pt-2 flex justify-between">
+            <span>⚠ Local Override</span>
+            {node.override_timeout_at ? (
+              <span className="text-gray-500">
+                Resets: {new Date(node.override_timeout_at).toLocaleTimeString()}
+              </span>
+            ) : (
+              <span className="text-gray-500">Permanent</span>
+            )}
+          </div>
+        )}
       </div>
     </Link>
   );

drb-frontend/components/NodeConfigModal.tsx

@@ -17,9 +17,11 @@ const PRESETS = [
 ];
 
 export function NodeConfigModal({ node, systems, onClose }: Props) {
-  const [systemId, setSystemId] = useState("");
-  const [preset, setPreset] = useState("rtl-sdr-v3");
-  const [ppm, setPpm] = useState("0");
+  const [systemId, setSystemId] = useState(node.assigned_system_id ?? "");
+  const [preset, setPreset] = useState(node.hardware_preset ?? "rtl-sdr-v3");
+  const [ppm, setPpm] = useState(node.ppm_override ? String(node.ppm_override) : "0");
+  const [nodeType, setNodeType] = useState(node.node_type ?? "");
+  const [enforceTimeout, setEnforceTimeout] = useState(node.enforce_override_timeout ?? true);
   const [saving, setSaving] = useState(false);
   const [error, setError] = useState<string | null>(null);
 
@@ -32,6 +34,10 @@ export function NodeConfigModal({ node, systems, onClose }: Props) {
     setSaving(true);
     setError(null);
     try {
+      await c2api.updateNode(node.node_id, {
+        node_type: nodeType,
+        enforce_override_timeout: enforceTimeout,
+      });
       await c2api.assignSystem(node.node_id, systemId, preset, ppmOverride);
       onClose();
     } catch (err) {
@@ -100,12 +106,41 @@ export function NodeConfigModal({ node, systems, onClose }: Props) {
             />
           </div>
 
+          <div>
+            <label className="block text-xs text-gray-400 mb-1">Node Type *</label>
+            <select
+              value={nodeType}
+              onChange={(e) => setNodeType(e.target.value)}
+              className="w-full bg-gray-800 border border-gray-700 rounded-lg px-3 py-2 text-white text-sm focus:outline-none focus:border-indigo-500"
+              required
+            >
+              <option value="">Select node type...</option>
+              <option value="fixed">Fixed Node (Standard)</option>
+              <option value="portable">Portable Node (Handheld)</option>
+            </select>
+          </div>
+
+          {nodeType === "fixed" && (
+            <div className="flex items-center gap-2 py-1">
+              <input
+                type="checkbox"
+                id="enforceTimeout"
+                checked={enforceTimeout}
+                onChange={(e) => setEnforceTimeout(e.target.checked)}
+                className="rounded bg-gray-800 border-gray-700 text-indigo-600 focus:ring-indigo-500 focus:ring-offset-gray-900"
+              />
+              <label htmlFor="enforceTimeout" className="text-xs text-gray-400 cursor-pointer select-none">
+                Enforce Local Override Timeout (24 hours)
+              </label>
+            </div>
+          )}
+
           {error && <p className="text-red-400 text-xs">{error}</p>}
 
           <div className="flex gap-3 pt-1">
             <button
               type="submit"
-              disabled={saving || !systemId}
+              disabled={saving || !systemId || !nodeType}
               className="flex-1 bg-indigo-600 hover:bg-indigo-500 disabled:opacity-50 text-white rounded-lg py-2 text-sm font-semibold transition-colors"
             >
               {saving ? "Saving…" : "Assign & Configure"}

drb-frontend/lib/c2api.ts

@@ -30,6 +30,12 @@ export const c2api = {
     if (ppmOverride !== undefined) params.set("ppm_override", String(ppmOverride));
     return request(`/nodes/${nodeId}/config/${systemId}?${params}`, { method: "POST" });
   },
+  ackOverride: (nodeId: string, timeoutMinutes: number = 1440) =>
+    request(`/nodes/${nodeId}/override/ack`, { method: "POST", body: JSON.stringify({ timeout_minutes: timeoutMinutes }) }),
+  resetOverride: (nodeId: string) =>
+    request(`/nodes/${nodeId}/override/reset`, { method: "POST" }),
+  updateNode: (id: string, body: { node_type?: string; enforce_override_timeout?: boolean }) =>
+    request(`/nodes/${id}`, { method: "PATCH", body: JSON.stringify(body) }),
 
   // Systems
   getSystems: () => request<unknown[]>("/systems"),

drb-frontend/lib/types.ts

@@ -52,6 +52,11 @@ export interface NodeRecord {
   approval_status: ApprovalStatus | null;
   hardware_preset?: string;
   ppm_override?: number | null;
+  node_type?: string;
+  enforce_override_timeout?: boolean;
+  is_overridden?: boolean;
+  override_system_id?: string | null;
+  override_timeout_at?: string | null;
 }
 
 export interface VocabularyPendingTerm {

infra/ansible/roles/deploy/handlers/main.yml

@@ -0,0 +1,13 @@
+---
+# The "Deploy Caddyfile" task notifies this. Without this file the play aborts
+# with "The requested handler 'Reload Caddy' was not found" — notify does not
+# tolerate a missing handler.
+#
+# reloaded, not restarted: caddy reload swaps config with zero downtime and
+# keeps existing TLS certs/connections; a restart drops every in-flight request.
+
+- name: Reload Caddy
+  ansible.builtin.systemd_service:
+    name: caddy
+    state: reloaded
+    enabled: true

infra/ansible/roles/deploy/tasks/main.yml

@@ -2,12 +2,19 @@
 # First-time setup: clone repo, write secrets, pull pre-built images and start stack.
 # Images are built and pushed by Gitea CI — this role never builds on the VM.
 
-- name: Clone repo (skipped if already present)
+# update: true (was false) — with update disabled, every re-run of this playbook
+# redeployed the code that happened to be on the VM at first clone, so any fix
+# pushed to main was invisible here and the only way to ship one was CI or a
+# manual pull. force: true discards local edits made on the VM; the templated
+# .env files and Caddyfile live outside git tracking, so nothing generated by
+# this role is at risk.
+- name: Clone or update repo
   git:
     repo: "{{ repo_url }}"
     dest: "{{ app_dir }}"
     version: main
-    update: false
+    update: true
+    force: true
   become: false
 
 - name: Set ownership of app directory

infra/ansible/roles/deploy/templates/Caddyfile.j2

@@ -1,4 +1,4 @@
-# Managed by Ansible — do not edit manually on the server.
+# Managed by Ansible — do not edit manually.
 
 api.{{ domain }} {
   reverse_proxy localhost:8888 {
@@ -6,7 +6,12 @@ api.{{ domain }} {
   }
 }
 
-app.{{ domain }} {
+# Frontend is served on the bare domain, not app.{{ domain }}: only drb and api
+# have public DNS records. A vhost for a name with no A record still starts,
+# but Caddy retries ACME against it forever and logs a failure each time.
+# To move it to app.{{ domain }}, create the A record first, then change this
+# line — the reverse_proxy target stays the same either way.
+{{ domain }} {
   reverse_proxy localhost:3000 {
     header_up X-Forwarded-For {remote_host}
   }

infra/ansible/roles/deploy/templates/root.env.j2

@@ -1,10 +1,19 @@
 # Top-level docker-compose environment — MQTT credentials and registry prefix.
 # Managed by Ansible. Do not edit manually.
+#
+# The passwords are $-escaped ($ -> $$). Compose INTERPOLATES this file, so a
+# raw "$fP" in a password is read as the variable $fP, warned about, and
+# replaced with an empty string. The env_file templates (c2-core.env.j2 etc.)
+# are NOT interpolated, so they keep the literal value — which means an
+# unescaped $ here silently gives mosquitto and c2-core two different
+# passwords and MQTT auth fails. Compose collapses $$ back to a single $, so
+# both sides end up with the real password.
+# Do not add the same escaping to the env_file templates; it would be literal.
 
 MQTT_C2_USER={{ vault_mqtt_c2_user }}
-MQTT_C2_PASS={{ vault_mqtt_c2_pass }}
+MQTT_C2_PASS={{ vault_mqtt_c2_pass | replace('$', '$$') }}
 MQTT_NODE_USER={{ vault_mqtt_node_user }}
-MQTT_NODE_PASS={{ vault_mqtt_node_pass }}
+MQTT_NODE_PASS={{ vault_mqtt_node_pass | replace('$', '$$') }}
 
 # Container registry prefix — docker compose uses this for image: ${REGISTRY}/name:latest
 REGISTRY={{ vault_registry }}

infra/ansible/site.yml

@@ -36,16 +36,33 @@
         path: /swapfile
         mode: "0600"
 
+    # mkswap refuses to touch a file that is already active as swap, so a
+    # re-run would fail here without this guard. The swap file survives
+    # reboots via the fstab entry below, so on any second run it IS active.
+    - name: Check whether the swap file is already active
+      command: swapon --show=NAME --noheadings
+      register: _active_swaps
+      changed_when: false
+      failed_when: false
+
     - name: Format swap file
       command: mkswap /swapfile
+      when: "'/swapfile' not in _active_swaps.stdout"
       register: _mkswap
       changed_when: _mkswap.rc == 0
 
+    # Guarded by the same check as mkswap above. The stderr test alone was not
+    # enough: an already-active swap file reports "Device or resource busy",
+    # not "already", so the original failed_when never matched it.
     - name: Enable swap
       command: swapon /swapfile
+      when: "'/swapfile' not in _active_swaps.stdout"
       register: _swapon
-      failed_when: _swapon.rc != 0 and 'already' not in _swapon.stderr
-      changed_when: _swapon.rc == 0
+      failed_when: >
+        _swapon.rc is defined and _swapon.rc != 0
+        and 'already' not in _swapon.stderr
+        and 'busy' not in _swapon.stderr
+      changed_when: _swapon.rc is defined and _swapon.rc == 0
 
     - name: Persist swap in fstab
       lineinfile:

infra/ansible/vault.yml.example

@@ -4,6 +4,13 @@
 # Edit later with:
 #   ansible-vault edit vault.yml
 
+# DO NOT put a literal "$" in any value here. Docker compose interpolates the
+# top-level .env, and depending on version it also interpolates env_file, so a
+# password like "aB$fPx" is read as the variable $fPx and silently replaced
+# with an empty string — on one side of the connection but not the other.
+# That produced "MQTT connect refused: Not authorized" with no obvious cause.
+# Generate with: openssl rand -hex 32  (hex output has no shell metacharacters)
+
 # ── MQTT ─────────────────────────────────────────────────────────────────────
 vault_mqtt_c2_user: drb-c2-core
 vault_mqtt_c2_pass: "CHANGE_ME"
@@ -22,7 +29,14 @@ vault_firestore_database: "c2-server"
 # ── Gitea Container Registry ──────────────────────────────────────────────────
 vault_registry_host: "git.vpn.cusano.net"
 vault_registry_user: "logan"
-vault_registry_token: ""                                   # Gitea access token with package:write scope
+vault_registry_token: ""                                   # Gitea access token, READ-ONLY package scope.
+                                                           # The VM only pulls (roles/deploy/tasks/main.yml:62-72);
+                                                           # nothing here pushes. Pushing is CI's job and uses a
+                                                           # separate write-scoped token (BUILD_TOKEN in Gitea
+                                                           # repo secrets). Keep them separate: this token sits on
+                                                           # an internet-facing VM, and a write-scoped one there
+                                                           # would let an attacker publish a poisoned image that
+                                                           # every future deploy and edge node would install.
 vault_registry: "git.vpn.cusano.net/logan"                # full image prefix
 
 # ── Discord Bot ───────────────────────────────────────────────────────────────