fix(wifi,fips): self-heal polkit rule + fast-retry anchors after daemon restart

Two fleet fixes that OTA can deliver (unlike the ISO-only polkit rule):

- WiFi (issue #99): nodes drive NetworkManager from a system-level service
  with no logind seat, so the stock polkit rule denies them and Wi-Fi setup
  fails with 'Insufficient privileges'. Fresh ISOs since 2026-05 ship the
  scoped rule, but OTA'd nodes never got it (OTA replaces binary + web UI,
  not host system config). Add a startup self-heal that installs the rule if
  missing and best-effort ensures polkitd — both wrapped so an offline/locked
  apt can never fail startup; the rule is written regardless so it activates
  once polkitd lands. Idempotent on the rule's unique subject.user marker.

- FIPS: regenerating fips.yaml (this build does, once, on first boot after
  the OTA) restarts the fips daemon; for a few seconds /run/fips/control.sock
  is gone and every seed-anchor dial fails, islanding the node until the next
  5-min tick. Detect that exact failure (all dials fail on control.sock) and
  retry in 15s instead — bounded to 8 fast retries/episode so a node with no
  fips daemon falls back to the steady cadence rather than busy-looping.

FIPS unit suite: 33/33 pass.

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

core/archipelago/src/bootstrap.rs

@@ -137,6 +137,13 @@ pub async fn ensure_doctor_installed() {
         Ok(false) => debug!("/opt/archipelago/apps already populated (or no installer copy)"),
         Err(e) => warn!("Apps dir repair failed (non-fatal): {:#}", e),
     }
+    match run_polkit_networkmanager_repair().await {
+        Ok(true) => info!(
+            "Installed NetworkManager polkit rule for the archipelago user — Wi-Fi setup enabled"
+        ),
+        Ok(false) => debug!("NetworkManager polkit rule already present"),
+        Err(e) => warn!("polkit NetworkManager repair failed (non-fatal): {:#}", e),
+    }
     match run_journald_dropin().await {
         Ok(true) => info!("Installed journald log-volume policy drop-in"),
         Ok(false) => debug!("journald log-volume policy already in place"),
@@ -442,6 +449,68 @@ exit 2
     }
 }
 
+/// Self-heal Wi-Fi setup on nodes that predate the polkit fix (issue #99).
+///
+/// Archipelago drives NetworkManager from a system-level systemd service
+/// (`User=archipelago`, no logind seat), so the stock NM polkit rule — which
+/// only authorizes `subject.local && subject.active` sessions — denies it, and
+/// "connect to Wi-Fi" fails with "Insufficient privileges". Fresh ISO installs
+/// since 2026-05 ship the rule below, but nodes that reached this build over
+/// OTA never got it (OTA replaces the binary + web UI, not host system config).
+///
+/// Install the scoped rule if it is missing, and best-effort ensure `polkitd`
+/// itself is present (without the daemon the rule is inert). Both are wrapped
+/// so an offline/locked apt or a missing package can never fail startup — the
+/// rule is still written so it takes effect once polkitd arrives (e.g. after an
+/// ISO reflash). Idempotent: keyed on the rule's unique `subject.user` marker.
+async fn run_polkit_networkmanager_repair() -> Result<bool> {
+    let script = r#"
+set -u
+RULE=/etc/polkit-1/rules.d/49-archipelago-networkmanager.rules
+MARKER='subject.user == "archipelago"'
+# Rule already installed — nothing to do.
+if grep -qF "$MARKER" "$RULE" 2>/dev/null; then
+    exit 0
+fi
+# The rule is inert without the polkit daemon. Older nodes (the ones that hit
+# issue #99) shipped without it. Try to install it, but never let apt failure
+# (offline node, locked dpkg, package unavailable) abort the heal — the rule is
+# written regardless so it activates whenever polkitd lands.
+if [ ! -d /usr/share/polkit-1 ] && ! command -v pkaction >/dev/null 2>&1; then
+    timeout 240 apt-get install -y --no-install-recommends polkitd >/dev/null 2>&1 \
+        || timeout 240 sh -c 'apt-get update >/dev/null 2>&1 && apt-get install -y --no-install-recommends polkitd >/dev/null 2>&1' \
+        || true
+fi
+mkdir -p /etc/polkit-1/rules.d
+cat > "$RULE" <<'RULEEOF'
+polkit.addRule(function(action, subject) {
+    if (subject.user == "archipelago" && action.id.indexOf("org.freedesktop.NetworkManager.") == 0) {
+        return polkit.Result.YES;
+    }
+});
+RULEEOF
+chmod 644 "$RULE"
+# Pick up the new rule. polkitd re-reads rules.d on reload; restart as a
+# fallback. Non-fatal if the unit name differs or the daemon is absent.
+systemctl reload polkit 2>/dev/null \
+    || systemctl restart polkit 2>/dev/null \
+    || systemctl restart polkit.service 2>/dev/null \
+    || true
+exit 2
+"#;
+    let status = host_sudo(&["sh", "-lc", script])
+        .await
+        .context("install NetworkManager polkit rule")?;
+    match status.code() {
+        Some(0) => Ok(false),
+        Some(2) => Ok(true),
+        _ => {
+            warn!("polkit NetworkManager repair helper exited with {}", status);
+            Ok(false)
+        }
+    }
+}
+
 async fn run_bitcoin_rpc_repair() -> Result<bool> {
     // Older installs can have a container-owned bitcoin.conf with only rpcauth
     // and printtoconsole. Repair it at startup so OTA fixes existing nodes

core/archipelago/src/server.rs

@@ -688,12 +688,27 @@ impl Server {
             let fips_peer_registry = fips_peer_registry.clone();
             tokio::spawn(async move {
                 tokio::time::sleep(Duration::from_secs(30)).await;
-                let mut interval = tokio::time::interval(Duration::from_secs(300));
+                // Steady cadence, but retry fast right after a daemon restart:
+                // regenerating fips.yaml (this build does, once, on first boot
+                // after the OTA) restarts the fips daemon, and for a few seconds
+                // `/run/fips/control.sock` is gone so every `fipsctl connect`
+                // fails and the node islands until the next tick. Detect that
+                // exact failure and retry in 15s instead of 5 min — bounded, so a
+                // node with no fips daemon falls back to the steady cadence
+                // rather than busy-looping.
+                const STEADY: Duration = Duration::from_secs(300);
+                const FAST: Duration = Duration::from_secs(15);
+                const MAX_FAST_RETRIES: u32 = 8; // ≤2 min of fast retries/episode
+                let mut fast_retries: u32 = 0;
                 loop {
-                    interval.tick().await;
+                    let mut daemon_restarting = false;
                     match crate::fips::anchors::load(&data_dir).await {
                         Ok(list) if !list.is_empty() => {
-                            let _ = crate::fips::anchors::apply(&list).await;
+                            let results = crate::fips::anchors::apply(&list).await;
+                            daemon_restarting = !results.is_empty()
+                                && results
+                                    .iter()
+                                    .all(|r| !r.ok && r.message.contains("control.sock"));
                         }
                         Ok(_) => { /* no seed anchors configured yet */ }
                         Err(e) => {
@@ -717,6 +732,15 @@ impl Server {
                             let _ = crate::fips::anchors::apply(&direct).await;
                         }
                     }
+
+                    let next = if daemon_restarting && fast_retries < MAX_FAST_RETRIES {
+                        fast_retries += 1;
+                        FAST
+                    } else {
+                        fast_retries = 0;
+                        STEADY
+                    };
+                    tokio::time::sleep(next).await;
                 }
             });
         }