deploy: hardware-instance templating, wlan0 boot watchdog, deploy-time warnings in Cockpit

- deploy.conf templates interface names/USB IDs (@TOKEN@ substitution) across
  ap/* configs so a dongle swap only needs deploy.conf edited, not the repo
  configs themselves; drops ap/rtw88.conf (old 2.4GHz dongle retired for the
  DWA-171, which needs no such power-save override).
- failover/van-wlan-watchdog: recovers wlan0 from NM's post-boot no-secrets
  wedge (a boot-time supplicant race, not a real credential failure).
- deploy.sh: warn() collects dependency/config warnings (missing python3-gps,
  python3-paho-mqtt, mobile-broadband-provider-info, grpcurl, gpsd; netplan
  drift; unedited example configs) into /var/lib/vanlink/deploy-warnings.json,
  rendered as an amber Cockpit card so they're visible without reading deploy
  output.

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

ap/10-van-ap.network

@@ -1,5 +1,5 @@
 [Match]
-Name=wlxc83a35a4ee55
+Name=@WIFI_5G_IFACE@
 
 [Link]
 RequiredForOnline=no

ap/11-van-ap-2g.network

@@ -1,5 +1,5 @@
 [Match]
-Name=wlxd8ec5e2faa8c
+Name=@WIFI_2G_IFACE@
 
 [Link]
 RequiredForOnline=no

ap/22-van-lan.network

@@ -2,7 +2,7 @@
 # gets DHCP/DNS from the same dnsmasq as Wi-Fi clients. NM must leave this device
 # alone (see van-ap-unmanaged.conf) for networkd to own it here.
 [Match]
-Name=enx00e04c331140
+Name=@LAN_USB_IFACE@
 
 [Link]
 RequiredForOnline=no

ap/50-van-wan.yaml

@@ -10,10 +10,11 @@ network:
   version: 2
   ethernets:
     # Starlink dish uplink (RTL8153 USB NIC, MAC-named — travels with the
-    # adapter). The /32 link route keeps the dish's management address reachable
+    # adapter, see STARLINK_IFACE in deploy.conf). The /32 link route keeps the
-    # no matter which WAN holds the default route: the dish answers on
+    # dish's management address reachable no matter which WAN holds the
-    # 192.168.100.1 (gRPC :9200) even while the uplink sits behind CGNAT.
+    # default route: the dish answers on 192.168.100.1 (gRPC :9200) even while
-    enxd8ec5eeb3512:
+    # the uplink sits behind CGNAT.
+    @STARLINK_IFACE@:
       renderer: NetworkManager
       optional: true
       dhcp4: true

ap/hostapd-2g.conf

@@ -1,4 +1,4 @@
-interface=wlxd8ec5e2faa8c
+interface=@WIFI_2G_IFACE@
 # Second, independent hostapd instance (hostapd-2g.service) — 2.4GHz band of the same
 # VanLink network, bridged into the same br0 segment as the 5GHz AP and the wired port.
 # Separate process on purpose: a USB wedge on one radio must never take down the other.
@@ -17,7 +17,7 @@ wmm_enabled=1
 # HT20 only — 40MHz in 2.4GHz overlaps most of the band and coexistence would force
 # it back to 20MHz near any neighbor anyway.
 ieee80211n=1
-ht_capab=[LDPC][SHORT-GI-20]
+ht_capab=[SHORT-GI-20]
 auth_algs=1
 wpa=2
 wpa_passphrase=1foot11foot11

ap/hostapd-2g.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=VanLink 2.4GHz AP (hostapd on wlxd8ec5e2faa8c, RTL8822BU)
+Description=VanLink 2.4GHz AP (hostapd on @WIFI_2G_IFACE@ — see deploy.conf for current hardware)
 # Same USB re-enumeration hazards as the 5GHz AP (see hostapd-restart.conf for the
 # full story): never stop retrying, and back off a few seconds so the USB device can
 # re-enumerate before the next attempt.

ap/hostapd.conf

@@ -1,4 +1,4 @@
-interface=wlxc83a35a4ee55
+interface=@WIFI_5G_IFACE@
 # Put the AP into br0 so Wi-Fi and the wired LAN port share one 10.42.0.0/24 segment.
 # hostapd adds the wlan to the bridge after setting AP mode; the bridge itself + its
 # wired member + the gateway IP are defined under /etc/systemd/network (2x-van-br0/lan).

ap/rtw88.conf

@@ -1,10 +0,0 @@
-# 2.4GHz AP dongle (Linksys WUSB6300 v2, RTL8822BU, rtw88_8822bu).
-# Deep power-save has no business on an always-on AP radio — same reasoning as the
-# rtw89 disable_ps_mode gotcha on the 5GHz dongle (rtw89.conf).
-options rtw88_core disable_lps_deep=Y
-# Don't let the driver switch a USB2-enumerated dongle up to USB3: USB3 signalling
-# radiates broadband noise right across the 2.4GHz band, and HT20 rates fit in USB2
-# easily. NOTE: this only blocks the driver's own USB2->3 switch — a dongle sitting in
-# a USB3 port still enumerates at SuperSpeed (it currently does); move it to a USB2
-# port if 2.4GHz range/interference ever looks poor.
-options rtw88_usb switch_usb_mode=N

ap/van-ap-unmanaged.conf

@@ -2,4 +2,4 @@
 # The AP wlans (5GHz + 2.4GHz) and the wired LAN ports (USB dongle + onboard
 # eth0) are all owned by systemd-networkd/hostapd (bridged into br0), so
 # NetworkManager must not touch them.
-unmanaged-devices=interface-name:wlxc83a35a4ee55;interface-name:wlxd8ec5e2faa8c;interface-name:enx00e04c331140;interface-name:eth0
+unmanaged-devices=interface-name:@WIFI_5G_IFACE@;interface-name:@WIFI_2G_IFACE@;interface-name:@LAN_USB_IFACE@;interface-name:eth0

cockpit/vanrouter/index.html

@@ -15,6 +15,11 @@
             <span id="updated" class="muted">loading…</span>
         </div>
 
+        <div class="card" id="deploywarn-card" style="display:none">
+            <h3>Deploy Warnings</h3>
+            <div id="deploywarn"></div>
+        </div>
+
         <div class="card">
             <h3>Access Points</h3>
             <div id="ap"></div>
@@ -45,6 +50,14 @@
             <div id="starlink"></div>
         </div>
 
+        <div class="card">
+            <div class="card-head">
+                <h3>Wi-Fi Networks</h3>
+                <button id="wifi-scan" class="btn">Scan</button>
+            </div>
+            <div id="wifi"><p class="muted">Click Scan to search for networks.</p></div>
+        </div>
+
         <div class="card">
             <h3>WAN / Uplinks</h3>
             <table>

cockpit/vanrouter/vanrouter.css

@@ -23,3 +23,7 @@ th { color: #6a6e73; font-weight: 600; }
 .active-wan { font-weight: 700; color: #0066cc; }
 .btn { margin-left: 6px; padding: 3px 10px; cursor: pointer; }
 .btn[disabled] { cursor: default; opacity: 0.5; }
+#deploywarn-card { border-color: #e08a00; }
+.warn-list { margin: 0; padding-left: 20px; }
+.warn-list li { background: #f5d9a8; color: #5f4414; border-radius: 4px;
+                padding: 4px 8px; margin: 4px 0; list-style: none; margin-left: -20px; }

cockpit/vanrouter/vanrouter.js

@@ -7,18 +7,20 @@
 // { superuser: "require" } which triggers Cockpit's admin (polkit) escalation.
 
 // AP radios (MAC-derived iface names, stable) — each runs its own hostapd unit.
+// Interface names/vendor ID below are templated from deploy.conf at deploy
+// time (see deploy.sh's render()) — edit deploy.conf, not the values here.
 const APS = [
-    { iface: "wlxc83a35a4ee55", unit: "hostapd",    band: "5GHz"   },  // RTL8852BU
+    { iface: "@WIFI_5G_IFACE@", unit: "hostapd",    band: "5GHz"   },
-    { iface: "wlxd8ec5e2faa8c", unit: "hostapd-2g", band: "2.4GHz" },  // RTL8822BU
+    { iface: "@WIFI_2G_IFACE@", unit: "hostapd-2g", band: "2.4GHz" },
 ];
 const PREFER_FILE = "/run/van-failover/prefer";  // van-failover reads this to pick the preferred WAN
 // Wired LAN bridge ports: clients behind them are found via the bridge FDB.
-const LAN_PORTS = { "eth0": "LAN (eth0)", "enx00e04c331140": "LAN (USB)" };
+const LAN_PORTS = { "eth0": "LAN (eth0)", "@LAN_USB_IFACE@": "LAN (USB)" };
 // Starlink dish: gRPC status API on the fixed management IP (reached via the /32
 // link route the netplan profile installs on the RTL8153 uplink).
-const STARLINK = { iface: "enxd8ec5eeb3512", dish: "192.168.100.1:9200" };
+const STARLINK = { iface: "@STARLINK_IFACE@", dish: "192.168.100.1:9200" };
 // Cellular modem (Quectel EC25-AF): used to find the USB device for a hard restart.
-const MODEM_USB_VENDOR = "2c7c";
+const MODEM_USB_VENDOR = "@MODEM_USB_VENDOR@";
 
 function run(args, opts) {
     return cockpit.spawn(args, Object.assign({ err: "message" }, opts || {}));
@@ -47,6 +49,7 @@ const STATUS_SCRIPT = (() => {
         add(`info${i}`,     `iw dev ${a.iface} info`);
         add(`stations${i}`, `iw dev ${a.iface} station dump`);
     });
+    add("deploywarn", "cat /var/lib/vanlink/deploy-warnings.json");
     add("neigh",    "ip -j neigh show dev br0");
     add("fdb",      "bridge -j fdb show br br0");
     add("leases",   "cat /var/lib/misc/dnsmasq.leases");
@@ -83,6 +86,21 @@ function parseJSON(text, fallback) {
     try { return JSON.parse(text); } catch (e) { return fallback; }
 }
 
+/* ---------- Deploy warnings (deploy.sh's collected warn() calls) ---------- */
+
+function renderDeployWarnings(dw) {
+    const card = document.getElementById("deploywarn-card");
+    const warnings = (dw && dw.warnings) || [];
+    if (!warnings.length) { card.style.display = "none"; return; }
+    card.style.display = "";
+    let html = `<ul class="warn-list">`;
+    warnings.forEach(w => { html += `<li>${esc(w)}</li>`; });
+    html += `</ul>`;
+    html += `<p class="muted">From last deploy (${esc(dw.deployed || "—")}) — ` +
+            `re-run <code>sudo ./deploy.sh</code> after fixing to clear.</p>`;
+    document.getElementById("deploywarn").innerHTML = html;
+}
+
 /* ---------- Access Point ---------- */
 
 function parseAP(a, i, secs) {
@@ -321,7 +339,7 @@ function renderFailover(fo) {
                ` <span class="muted">· updated ${esc(fo.updated || "")}</span></p>`;
     html += `<table><thead><tr><th>WAN</th><th>Priority</th><th>Device</th><th>Status</th><th>Metric</th></tr></thead><tbody>`;
     fo.wans.forEach(w => {
-        const status = !w.present ? `<span class="pill">absent</span>`
+        const status = !w.present ? `<span class="pill warn">absent</span>`
                      : w.up       ? `<span class="pill ok">up</span>`
                                   : `<span class="pill bad">down</span>`;
         const prio = w.preferred ? `${esc(w.priority)} <span class="muted">(preferred)</span>` : esc(w.priority);
@@ -333,6 +351,106 @@ function renderFailover(fo) {
     el.innerHTML = html;
 }
 
+/* ---------- Wi-Fi network selector (wlan0 WAN) ---------- */
+
+// The onboard radio used for the WiFi WAN — unlike the AP dongles it's never
+// templated, this host only ever has the one.
+const WIFI_IFACE = "wlan0";
+
+// SSIDs the van's own AP radios are currently beaconing (kept live from refresh()'s
+// `iw dev ... info` parse, not hardcoded) — wlan0 "connecting" to its own AP would be
+// a nonsensical loop, so those rows get their Connect button disabled below.
+let ownAPSSIDs = new Set();
+
+// nmcli -t escapes ':' inside field values as '\:' — split on unescaped ':' only.
+// SSIDs are environment-controlled strings (the van parks near arbitrary APs), so
+// worth handling properly rather than a naive split(":").
+function splitNmcli(line) {
+    const parts = [];
+    let cur = "";
+    for (let i = 0; i < line.length; i++) {
+        if (line[i] === "\\" && line[i + 1] === ":") { cur += ":"; i++; }
+        else if (line[i] === ":") { parts.push(cur); cur = ""; }
+        else cur += line[i];
+    }
+    parts.push(cur);
+    return parts;
+}
+
+function renderWifiList(rows) {
+    const el = document.getElementById("wifi");
+    if (!rows.length) {
+        el.innerHTML = `<p class="muted">No networks found. Try Scan.</p>`;
+        return;
+    }
+    let html = `<table><thead><tr><th>SSID</th><th>Signal</th><th>Security</th><th></th></tr></thead><tbody>`;
+    rows.forEach(r => {
+        const ownAP = ownAPSSIDs.has(r.ssid);
+        const label = r.inUse ? "Connected" : ownAP ? "Own AP" : "Connect";
+        html += `<tr><td>${r.inUse ? "★ " : ""}${esc(r.ssid)}</td>` +
+                `<td>${esc(r.signal)}%</td><td>${esc(r.security || "open")}</td>` +
+                `<td class="acts"><button class="btn wifi-connect"${ownAP ? ` title="This is the van's own VanLink AP — wlan0 can't usefully connect to it"` : ""}>${label}</button></td></tr>`;
+    });
+    html += `</tbody></table>`;
+    el.innerHTML = html;
+    el.querySelectorAll(".wifi-connect").forEach((btn, i) => {
+        const r = rows[i];
+        btn.disabled = r.inUse || ownAPSSIDs.has(r.ssid);
+        btn.onclick = () => connectWifi(r);
+    });
+}
+
+async function scanWifi() {
+    const el = document.getElementById("wifi");
+    el.innerHTML = `<p class="muted">Scanning…</p>`;
+    try {
+        // Actually triggering a rescan (not just listing NM's cache) needs the
+        // org.freedesktop.NetworkManager.wifi.scan polkit action, which a plain
+        // Cockpit session doesn't have — without escalation this silently returns
+        // only the cached/connected AP instead of erroring.
+        const out = await run(["nmcli", "-t", "-f", "IN-USE,SSID,SIGNAL,SECURITY",
+                                "device", "wifi", "list", "ifname", WIFI_IFACE, "--rescan", "yes"],
+                               { superuser: "require" });
+        const seen = new Set();
+        const rows = out.trim().split("\n").filter(Boolean).map(splitNmcli).map(f => ({
+            inUse: f[0].indexOf("*") !== -1, ssid: f[1], signal: f[2], security: f[3],
+        })).filter(r => {
+            if (!r.ssid || seen.has(r.ssid)) return false;
+            seen.add(r.ssid);
+            return true;
+        }).sort((a, b) => (b.inUse - a.inUse) || (parseInt(b.signal, 10) - parseInt(a.signal, 10)));
+        renderWifiList(rows);
+    } catch (e) {
+        el.innerHTML = `<p class="muted">Scan failed: ${esc(e.message)}</p>`;
+    }
+}
+
+async function connectWifi(r) {
+    if (ownAPSSIDs.has(r.ssid)) return;  // belt-and-suspenders; button is disabled too
+    // Try without a password first — reuses a saved profile's stored secret (or
+    // just works for an open network); only prompt if NM actually needs one.
+    try {
+        await run(["nmcli", "device", "wifi", "connect", r.ssid, "ifname", WIFI_IFACE],
+                  { superuser: "require" });
+        scanWifi();
+        return;
+    } catch (e) {
+        if (!/secret|password|psk/i.test(e.message || "")) {
+            window.alert("Connect failed: " + e.message);
+            return;
+        }
+    }
+    const pwd = window.prompt(`Password for "${r.ssid}":`);
+    if (!pwd) return;
+    try {
+        await run(["nmcli", "device", "wifi", "connect", r.ssid, "password", pwd, "ifname", WIFI_IFACE],
+                  { superuser: "require" });
+    } catch (e) { window.alert("Connect failed: " + e.message); }
+    scanWifi();
+}
+
+document.getElementById("wifi-scan").onclick = scanWifi;
+
 /* ---------- WAN / uplinks ---------- */
 
 // mmcli -K key-values -> { netdev, signal, tech, operator } (null if no modem).
@@ -402,16 +520,24 @@ function parseWAN(secs) {
     return devs;
 }
 
+// NM device states that count as "ready to serve traffic" vs. transient vs.
+// broken/unusable — drives the state-column pill color.
+const WAN_STATE_PILL = { connected: "ok", connecting: "warn" };
+
 function renderWAN(devs) {
     const tb = document.getElementById("wan");
     tb.innerHTML = "";
     devs.forEach(d => {
-        const isUp = d.state === "connected";
+        const isConnected = d.state === "connected";
+        // No carrier: nmcli can't connect a device with nothing on the other
+        // end of the wire, so the button would just fail — disable it rather
+        // than let it produce a silent "Toggle failed" alert.
+        const noCarrier = d.state === "unavailable";
         const tr = document.createElement("tr");
         tr.innerHTML =
             `<td class="${d.active ? "active-wan" : ""}">${d.active ? "★ " : ""}${esc(d.device)}</td>` +
             `<td>${esc(d.type)}</td>` +
-            `<td>${esc(d.state)}</td>` +
+            `<td><span class="pill ${WAN_STATE_PILL[d.state] || "bad"}">${esc(d.state)}</span></td>` +
             `<td>${esc(d.ip || "—")}</td>` +
             `<td>${d.signal || "—"}</td>` +
             `<td>${d.metric != null ? esc(d.metric) : "—"}</td>` +
@@ -428,8 +554,9 @@ function renderWAN(devs) {
         }
         const tog = document.createElement("button");
         tog.className = "btn";
-        tog.textContent = isUp ? "Down" : "Up";
+        tog.textContent = isConnected ? "Disconnect" : "Connect";
-        tog.onclick = () => toggleWAN(d, isUp);
+        tog.disabled = !isConnected && noCarrier;
+        tog.onclick = () => toggleWAN(d, isConnected);
         acts.appendChild(tog);
 
         if (d.type === "gsm") {
@@ -456,9 +583,9 @@ async function preferWAN(chosen) {
     setTimeout(refresh, 4500);  // daemon enforces on its next probe loop
 }
 
-async function toggleWAN(d, isUp) {
+async function toggleWAN(d, isConnected) {
     try {
-        const verb = isUp ? "disconnect" : "connect";
+        const verb = isConnected ? "disconnect" : "connect";
         await run(["nmcli", "device", verb, d.nmdev], { superuser: "require" });
     } catch (e) { window.alert("Toggle failed: " + e.message); }
     refresh();
@@ -492,7 +619,9 @@ async function restartAP(unit) {
 async function refresh() {
     try {
         const secs = parseSections(await sh(STATUS_SCRIPT));
+        renderDeployWarnings(parseJSON(secs.deploywarn, null));
         const aps = APS.map((a, i) => parseAP(a, i, secs));
+        ownAPSSIDs = new Set(aps.map(a => a.ssid).filter(Boolean));
         renderAPs(aps);
         renderClients(collectClients(aps, secs, parseClientDir(secs)));
         renderThermal(parseJSON(secs.thermal, null));

deploy.conf

@@ -0,0 +1,26 @@
+# deploy.conf — hardware-instance identifiers for this Pi's vanlink deployment.
+#
+# These are the values that change when a USB Wi-Fi dongle, LAN adapter, or
+# modem gets physically swapped (MAC-derived interface names are stable per
+# physical device, but change when the device changes). Edit here and run
+# `sudo ./deploy.sh` — it substitutes @TOKEN@ placeholders in the repo's
+# config templates with these values before installing them.
+#
+# Find a new device's interface name after plugging it in: `iw dev` (wifi) or
+# `ip -br link` (wired). USB vendor ID: `lsusb`.
+# Preview a rendered file without deploying: `sudo ./deploy.sh render <file>`
+
+# 5GHz AP radio (currently: Realtek RTL8852BU, driver rtw89_8852bu)
+WIFI_5G_IFACE=wlxc83a35a4ee55
+
+# 2.4GHz AP radio (currently: D-Link DWA-171, RTL8821CU, driver rtw88_8821cu)
+WIFI_2G_IFACE=wlx3c3332002066
+
+# Wired LAN port, USB-attached gigabit adapter (RTL8153-family)
+LAN_USB_IFACE=enx00e04c331140
+
+# Starlink dish uplink, USB-attached gigabit adapter (RTL8153-family)
+STARLINK_IFACE=enxd8ec5eeb3512
+
+# Cellular modem USB vendor ID (Quectel EC25-AF)
+MODEM_USB_VENDOR=2c7c

deploy.sh

@@ -1,49 +1,98 @@
 #!/usr/bin/env bash
 # Deploy vanlink configs/scripts (Pi 4 "wan" port) to their system locations.
 # Usage:  cd ~/vanlink && sudo ./deploy.sh
+#         sudo ./deploy.sh render <file>   # preview a templated file on stdout
 # Idempotent. Netplan (wlan0 + Starlink NIC = NM-managed WANs; eth0 is a LAN
 # port on br0) is NOT deployed here — reference copy in ap/50-van-wan.yaml,
 # applied once manually (apply flaps uplinks). We do check it for drift below.
 set -euo pipefail
 cd "$(dirname "$(readlink -f "$0")")"
+
+# deploy.conf holds hardware-instance identifiers (interface names, USB vendor
+# IDs) that change when a dongle/adapter gets physically swapped. Config files
+# below carry @TOKEN@ placeholders substituted from these variables via
+# render()/install_rendered() — edit deploy.conf, not the individual configs.
+set -a
+source ./deploy.conf
+set +a
+
+render() {  # render <file> -> stdout, with @TOKEN@ placeholders substituted
+    sed -e "s|@WIFI_5G_IFACE@|$WIFI_5G_IFACE|g" \
+        -e "s|@WIFI_2G_IFACE@|$WIFI_2G_IFACE|g" \
+        -e "s|@LAN_USB_IFACE@|$LAN_USB_IFACE|g" \
+        -e "s|@STARLINK_IFACE@|$STARLINK_IFACE|g" \
+        -e "s|@MODEM_USB_VENDOR@|$MODEM_USB_VENDOR|g" \
+        "$1"
+}
+install_rendered() {  # install_rendered <src> <dst> [mode]
+    local tmp
+    tmp=$(mktemp)
+    render "$1" > "$tmp"
+    install -D -m"${3:-0644}" "$tmp" "$2"
+    rm -f "$tmp"
+}
+
+if [ "${1:-}" = "render" ]; then
+    [ -n "${2:-}" ] || { echo "Usage: $0 render <file>"; exit 1; }
+    render "$2"
+    exit 0
+fi
+
 [ "$(id -u)" = 0 ] || { echo "Run with sudo (writes to /etc, /usr)."; exit 1; }
 
+# Collected below and persisted to WARNINGS_FILE so the Cockpit vanrouter page
+# can surface deploy-time issues (missing deps, unedited example configs, drift)
+# without someone having to remember to scroll back through deploy output.
+WARNINGS=()
+WARNINGS_FILE=/var/lib/vanlink/deploy-warnings.json
+warn() {  # warn <message...> — prints "   -> <message>" (as before) and records it
+    echo "   -> $*"
+    WARNINGS+=("$*")
+}
+write_warnings() {
+    install -d -m0755 "$(dirname "$WARNINGS_FILE")"
+    {
+        printf '{\n  "deployed": "%s",\n  "warnings": [' "$(date -Iseconds)"
+        local first=1 w e
+        for w in "${WARNINGS[@]}"; do
+            [ "$first" = 1 ] || printf ','
+            first=0
+            e=${w//\\/\\\\}; e=${e//\"/\\\"}
+            printf '\n    "%s"' "$e"
+        done
+        printf '\n  ]\n}\n'
+    } > "$WARNINGS_FILE"
+}
+
 echo "== netplan drift check =="
 # Netplan is never installed by this script (applying it flaps the uplinks —
 # see note below), so it's easy to edit ap/50-van-wan.yaml and forget the
 # manual `netplan apply` step. Warn loudly rather than silently drifting.
 if [ ! -f /etc/netplan/50-van-wan.yaml ]; then
-    echo "   -> WARNING: /etc/netplan/50-van-wan.yaml is missing. Repo config"
+    warn "netplan: /etc/netplan/50-van-wan.yaml is missing — repo config was never deployed. Run: sudo ./deploy.sh render ap/50-van-wan.yaml | sudo tee /etc/netplan/50-van-wan.yaml && sudo netplan generate && sudo netplan apply"
-    echo "      was never deployed to this system. Run manually:"
+elif ! diff -q <(render ap/50-van-wan.yaml) /etc/netplan/50-van-wan.yaml >/dev/null 2>&1; then
-    echo "        sudo cp ap/50-van-wan.yaml /etc/netplan/50-van-wan.yaml"
+    warn "netplan: /etc/netplan/50-van-wan.yaml differs from ap/50-van-wan.yaml (rendered). Deploy manually: sudo ./deploy.sh render ap/50-van-wan.yaml | sudo tee /etc/netplan/50-van-wan.yaml && sudo netplan generate && sudo netplan apply"
-    echo "        sudo netplan generate && sudo netplan apply"
+    diff -u /etc/netplan/50-van-wan.yaml <(render ap/50-van-wan.yaml) || true
-elif ! diff -q ap/50-van-wan.yaml /etc/netplan/50-van-wan.yaml >/dev/null 2>&1; then
-    echo "   -> WARNING: /etc/netplan/50-van-wan.yaml differs from ap/50-van-wan.yaml."
-    diff -u /etc/netplan/50-van-wan.yaml ap/50-van-wan.yaml || true
-    echo "      Deploy the change manually:"
-    echo "        sudo cp ap/50-van-wan.yaml /etc/netplan/50-van-wan.yaml"
-    echo "        sudo netplan generate && sudo netplan apply"
 fi
 
 echo "== access point =="
-install -D -m0644 ap/hostapd.conf           /etc/hostapd/hostapd.conf
+install_rendered ap/hostapd.conf            /etc/hostapd/hostapd.conf
 install -D -m0644 ap/hostapd-restart.conf   /etc/systemd/system/hostapd.service.d/restart.conf
 install -D -m0644 ap/default-hostapd        /etc/default/hostapd
-install -D -m0644 ap/hostapd-2g.conf        /etc/hostapd/hostapd-2g.conf
+install_rendered ap/hostapd-2g.conf         /etc/hostapd/hostapd-2g.conf
-install -D -m0644 ap/hostapd-2g.service     /etc/systemd/system/hostapd-2g.service
+install_rendered ap/hostapd-2g.service      /etc/systemd/system/hostapd-2g.service
-install -D -m0644 ap/11-van-ap-2g.network   /etc/systemd/network/11-van-ap-2g.network
+install_rendered ap/11-van-ap-2g.network    /etc/systemd/network/11-van-ap-2g.network
 install -D -m0644 ap/van-ap-watchdog-2g.service /etc/systemd/system/van-ap-watchdog-2g.service
-install -D -m0644 ap/rtw88.conf             /etc/modprobe.d/rtw88.conf
 install -D -m0755 ap/van-ap-watchdog        /usr/local/sbin/van-ap-watchdog
 install -D -m0644 ap/van-ap-watchdog.service /etc/systemd/system/van-ap-watchdog.service
 install -D -m0644 ap/van-ap-dnsmasq.conf    /etc/van-ap/dnsmasq.conf
 install -D -m0644 ap/van-ap-dnsmasq.service /etc/systemd/system/van-ap-dnsmasq.service
-install -D -m0644 ap/10-van-ap.network      /etc/systemd/network/10-van-ap.network
+install_rendered ap/10-van-ap.network       /etc/systemd/network/10-van-ap.network
 install -D -m0644 ap/20-van-br0.netdev      /etc/systemd/network/20-van-br0.netdev
 install -D -m0644 ap/21-van-br0.network     /etc/systemd/network/21-van-br0.network
-install -D -m0644 ap/22-van-lan.network     /etc/systemd/network/22-van-lan.network
+install_rendered ap/22-van-lan.network      /etc/systemd/network/22-van-lan.network
 install -D -m0644 ap/23-van-lan-eth0.network /etc/systemd/network/23-van-lan-eth0.network
-install -D -m0644 ap/van-ap-unmanaged.conf  /etc/NetworkManager/conf.d/van-ap-unmanaged.conf
+install_rendered ap/van-ap-unmanaged.conf   /etc/NetworkManager/conf.d/van-ap-unmanaged.conf
 # Mask dracut's initramfs-generated catch-all (/run/systemd/network/
 # zzzz-dracut-default.network, regenerated every boot): it matches every
 # unconfigured link, so networkd co-managed the NM-owned WANs — a second
@@ -61,15 +110,34 @@ install -D -m0644 failover/config.json          /etc/van-failover/config.json
 install -D -m0644 failover/van-failover.service /etc/systemd/system/van-failover.service
 install -D -m0755 failover/50-disable-eee       /etc/NetworkManager/dispatcher.d/50-disable-eee
 install -D -m0644 failover/99-van-arp.conf      /etc/sysctl.d/99-van-arp.conf
+# Backstop for wlan0's post-boot NM no-secrets wedge (see the script's docstring).
+install -D -m0755 failover/van-wlan-watchdog         /usr/local/sbin/van-wlan-watchdog
+install -D -m0644 failover/van-wlan-watchdog.service /etc/systemd/system/van-wlan-watchdog.service
+
+echo "== cellular modem (GSM/LTE) =="
+# NM's gsm.auto-config APN lookup needs this apt-only carrier database; without
+# it even the right APN can't be auto-detected, and MVNOs (e.g. Koodo, which
+# isn't listed under its own name — only under host network "Telus Mobility")
+# often aren't in it anyway, so the modem's NM connection profile may still
+# need an explicit gsm.apn set by hand regardless.
+dpkg -s mobile-broadband-provider-info >/dev/null 2>&1 \
+    || warn "mobile-broadband-provider-info missing (apt install mobile-broadband-provider-info) — GSM APN auto-config will fail"
 
 echo "== cockpit plugin =="
 install -d /usr/share/cockpit/vanrouter
-install -m0644 cockpit/vanrouter/* /usr/share/cockpit/vanrouter/
+for f in cockpit/vanrouter/*; do
+    b=$(basename "$f")
+    if [ "$b" = "vanrouter.js" ]; then
+        install_rendered "$f" "/usr/share/cockpit/vanrouter/$b"
+    else
+        install -m0644 "$f" "/usr/share/cockpit/vanrouter/$b"
+    fi
+done
 # Bridge fd headroom (Python bridge frees spawn pipes only at GC; 1024 is too tight)
 install -D -m0644 cockpit/cockpit-session-nofile.conf /etc/systemd/system/cockpit-session@.service.d/nofile.conf
 # The Starlink card queries the dish's gRPC API; grpcurl isn't packaged in apt.
 command -v grpcurl >/dev/null 2>&1 \
-    || echo "   -> grpcurl missing (Starlink card will say so): install linux_arm64 binary from github.com/fullstorydev/grpcurl/releases"
+    || warn "grpcurl missing (Starlink card will say so): install linux_arm64 binary from github.com/fullstorydev/grpcurl/releases"
 
 echo "== gps (cellular modem GNSS -> gpsd) =="
 if dpkg -s gpsd >/dev/null 2>&1; then
@@ -77,7 +145,7 @@ if dpkg -s gpsd >/dev/null 2>&1; then
     install -D -m0644 gps/gpsd.default       /etc/default/gpsd
     udevadm control --reload
 else
-    echo "   -> gpsd not installed (apt install gpsd gpsd-clients) — skipping GPS setup"
+    warn "gpsd not installed (apt install gpsd gpsd-clients) — skipping GPS setup"
 fi
 # OwnTracks publisher: gpsd fix -> MQTT (broker + creds live only on the
 # system, 0600 — same pattern as pushover.json).
@@ -85,10 +153,12 @@ install -D -m0755 gps/van-gps-owntracks         /usr/local/sbin/van-gps-owntrack
 install -D -m0644 gps/van-gps-owntracks.service /etc/systemd/system/van-gps-owntracks.service
 if [ ! -f /etc/van-gps/config.json ]; then
     install -D -m0600 gps/config.json.example /etc/van-gps/config.json
-    echo "   -> seeded /etc/van-gps/config.json (EDIT IT: add MQTT username + password)"
+    warn "seeded /etc/van-gps/config.json (EDIT IT: add MQTT username + password)"
 fi
+python3 -c 'import gps' 2>/dev/null \
+    || warn "python3-gps missing (apt install python3-gps) — van-gps-owntracks won't start"
 python3 -c 'import paho.mqtt' 2>/dev/null \
-    || echo "   -> python3-paho-mqtt missing (apt install python3-paho-mqtt) — van-gps-owntracks won't start"
+    || warn "python3-paho-mqtt missing (apt install python3-paho-mqtt) — van-gps-owntracks won't start"
 
 echo "== thermal monitor =="
 install -D -m0755 power/van-thermal         /usr/local/sbin/van-thermal
@@ -98,7 +168,7 @@ install -D -m0644 power/van-thermal.service /etc/systemd/system/van-thermal.serv
 # under /etc/van-battery/ for parity with wayback's van-thermal default.
 if [ ! -f /etc/van-battery/pushover.json ]; then
     install -D -m0600 power/pushover.json.example /etc/van-battery/pushover.json
-    echo "   -> seeded /etc/van-battery/pushover.json (EDIT IT: add Pushover token + user)"
+    warn "seeded /etc/van-battery/pushover.json (EDIT IT: add Pushover token + user)"
 fi
 
 echo "== home assistant =="
@@ -121,10 +191,10 @@ systemctl daemon-reexec
 # its wait-online would just stall network-online.target. NM-wait-online covers WANs.
 systemctl mask systemd-networkd-wait-online.service >/dev/null 2>&1 || true
 systemctl unmask hostapd >/dev/null 2>&1 || true
-systemctl enable regdomain.service hostapd hostapd-2g van-ap-dnsmasq nftables systemd-networkd van-failover van-thermal van-ap-watchdog van-ap-watchdog-2g van-gps-owntracks >/dev/null 2>&1 || true
+systemctl enable regdomain.service hostapd hostapd-2g van-ap-dnsmasq nftables systemd-networkd van-failover van-thermal van-ap-watchdog van-ap-watchdog-2g van-wlan-watchdog van-gps-owntracks >/dev/null 2>&1 || true
 # bluetooth: host BlueZ serves the onboard hci0 to the HA container over D-Bus
 systemctl enable --now bluetooth >/dev/null 2>&1 || true
-systemctl start homeassistant || echo "   -> homeassistant failed to start (podman/quadlet — check journalctl -u homeassistant)"
+systemctl start homeassistant || warn "homeassistant failed to start (podman/quadlet — check journalctl -u homeassistant)"
 systemctl restart van-thermal
 systemctl restart van-gps-owntracks
 # Pick up unmanaged-devices changes so NM releases/keeps the right interfaces.
@@ -132,7 +202,7 @@ nmcli general reload 2>/dev/null || systemctl reload NetworkManager 2>/dev/null
 # restart in dependency order: bridge + members first, then hostapd enslaves the
 # radios, then dnsmasq binds br0, then NAT/failover
 systemctl restart systemd-networkd
-systemctl restart van-ap-dnsmasq nftables van-failover
+systemctl restart van-ap-dnsmasq nftables van-failover van-wlan-watchdog
 # The AP radios live on the USB hub and may be absent; the start then fails but
 # Restart=always keeps retrying and claims them the moment they enumerate.
 systemctl restart hostapd hostapd-2g \
@@ -141,11 +211,13 @@ systemctl restart hostapd hostapd-2g \
 systemctl restart van-ap-watchdog van-ap-watchdog-2g
 networkctl reload 2>/dev/null || true
 
+write_warnings
+
 echo
 echo "Deployed. NOTE: until the USB hub (AP radios + LAN/Starlink adapters) is"
 echo "plugged in, hostapd/hostapd-2g just retry every 5s — that is by design."
 echo "Verify (with hub present):"
-echo "  iw dev wlxc83a35a4ee55 info | grep -E 'ssid|channel|width'"
+echo "  iw dev $WIFI_5G_IFACE info | grep -E 'ssid|channel|width'"
-echo "  iw dev wlxd8ec5e2faa8c info | grep -E 'ssid|channel|width'"
+echo "  iw dev $WIFI_2G_IFACE info | grep -E 'ssid|channel|width'"
 echo "  cat /run/van-failover/state.json"
 echo "  cat /run/van-thermal/state.json"

failover/van-wlan-watchdog

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""van-wlan-watchdog — recover wlan0 from NetworkManager's post-boot no-secrets wedge.
+
+Seen on 2026-07-30: wlan0 (onboard radio, used as the WiFi WAN) sometimes fails its
+very first post-boot association attempt with a spurious supplicant "psk mismatch"
+(a boot-time brcmfmac firmware/regulatory race, not a real credential problem — a
+second attempt with the *same* stored secret succeeds immediately). NetworkManager
+treats any handshake failure it reads as bad secrets as terminal: it does not retry
+autoconnect after a no-secrets failure, so the device just sits in `disconnected`
+until something explicitly re-triggers it. This is that trigger.
+
+Deliberately does NOT hardcode a connection/SSID name: which WiFi network wlan0 uses
+changes with wherever the van is parked (home, a campsite, a neighbour's AP — see
+config profiles managed from Cockpit's Networking tab or the Wi-Fi selector on the Van
+Router page). `nmcli device connect wlan0` lets NM pick amongst whatever profiles are
+saved and in range on its own, exactly like its normal autoconnect would.
+
+Bounded to a few minutes after boot, then exits — this is a backstop for the boot race
+above, not a permanent watcher. It must NOT fight a deliberate later disconnect (e.g.
+the Cockpit "Disconnect" button), which is why it doesn't loop forever.
+
+Usage: van-wlan-watchdog [device]
+Defaults to wlan0 (the AP radios are separate USB dongles, watched by
+van-ap-watchdog instead).
+"""
+
+import subprocess
+import sys
+import time
+
+DEVICE = sys.argv[1] if len(sys.argv) > 1 else "wlan0"
+INTERVAL = 15           # seconds between checks
+BUDGET_S = 8 * INTERVAL  # ~2 minutes of retries after boot, then give up quietly
+
+
+def log(msg, level="info"):
+    # systemd journal severity prefixes (sd-daemon), same convention as van-ap-watchdog.
+    pri = {"info": "<6>", "warn": "<4>", "crit": "<2>"}.get(level, "<6>")
+    print(pri + msg, flush=True)
+
+
+def device_state(dev):
+    """NM's state word for dev (e.g. 'connected', 'disconnected', 'unavailable'), or
+    None if nmcli failed or the device isn't known to NM yet."""
+    try:
+        out = subprocess.run(
+            ["nmcli", "-t", "-f", "GENERAL.STATE", "device", "show", dev],
+            capture_output=True, text=True, timeout=10,
+        ).stdout.strip()
+    except (OSError, subprocess.SubprocessError) as e:
+        log(f"nmcli device show {dev} failed: {e}", "warn")
+        return None
+    # terse output looks like "GENERAL.STATE:30 (disconnected)"
+    if "(" in out and out.endswith(")"):
+        return out.rsplit("(", 1)[1][:-1]
+    return None
+
+
+def connect(dev):
+    log(f"{dev} is disconnected — nudging NM to reconnect (autoconnect doesn't retry "
+        f"after a no-secrets failure, only manual/dispatcher re-activation does)", "warn")
+    r = subprocess.run(["nmcli", "device", "connect", dev],
+                       capture_output=True, text=True, timeout=45)
+    if r.returncode == 0:
+        log(f"{dev} reconnected")
+    else:
+        log(f"nmcli device connect {dev} returned {r.returncode}: {r.stderr.strip()}", "warn")
+
+
+def main():
+    log(f"van-wlan-watchdog up: watching {DEVICE} for up to {BUDGET_S}s after boot")
+    elapsed = 0
+    while elapsed < BUDGET_S:
+        state = device_state(DEVICE)
+        if state == "disconnected":
+            connect(DEVICE)
+        elif state == "connected":
+            log(f"{DEVICE} connected — exiting")
+            return
+        # "unavailable" (no known/in-range AP), "unmanaged", or unreadable: nothing to
+        # nudge — retrying nmcli device connect would just fail again.
+        time.sleep(INTERVAL)
+        elapsed += INTERVAL
+    log(f"{DEVICE} still not connected after {BUDGET_S}s — giving up "
+        f"(leaving it for manual/Cockpit reconnect from here on)", "warn")
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except KeyboardInterrupt:
+        sys.exit(0)

failover/van-wlan-watchdog.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=wlan0 boot-reconnect backstop (NM no-secrets wedge after a boot-time supplicant glitch)
+After=NetworkManager.service
+Wants=NetworkManager.service
+
+[Service]
+Type=simple
+ExecStart=/usr/local/sbin/van-wlan-watchdog
+
+[Install]
+WantedBy=multi-user.target