Merge remote-tracking branch 'gitea-ai/fix/companion-autologin-replay-intro'

core/archipelago/src/container/prod_orchestrator.rs

@@ -301,6 +301,33 @@ fn unrepairable_ownership() -> &'static std::sync::Mutex<std::collections::HashS
     SET.get_or_init(|| std::sync::Mutex::new(std::collections::HashSet::new()))
 }
 
+/// Per-container timestamp of the last volume-ownership sweep. The sweep's
+/// write-probes are `podman exec`s into EVERY running container; running them
+/// on every 30s reconcile tick meant six-plus cross-context exec attempts per
+/// tick forever — a permanent conmon "Failed to create container" storm on
+/// hosts where exec from the backend's cgroup context fails (Debian 13 first
+/// boot, 2026-07-19). Ownership drift is an install/OTA-time event, not a
+/// steady-state one: sweep each container on the first pass after it appears,
+/// then at most once per hour.
+fn ownership_sweep_due(name: &str) -> bool {
+    const SWEEP_INTERVAL: std::time::Duration = std::time::Duration::from_secs(60 * 60);
+    static LAST: std::sync::OnceLock<
+        std::sync::Mutex<std::collections::HashMap<String, std::time::Instant>>,
+    > = std::sync::OnceLock::new();
+    let map = LAST.get_or_init(|| std::sync::Mutex::new(std::collections::HashMap::new()));
+    let Ok(mut map) = map.lock() else {
+        return true;
+    };
+    let now = std::time::Instant::now();
+    match map.get(name) {
+        Some(last) if now.duration_since(*last) < SWEEP_INTERVAL => false,
+        _ => {
+            map.insert(name.to_string(), now);
+            true
+        }
+    }
+}
+
 /// App-agnostic, userns-mapping-proof volume-ownership repair for a RUNNING
 /// container.
 ///
@@ -1739,6 +1766,11 @@ impl ProdContainerOrchestrator {
                 if crate::app_ops::lifecycle_op_in_flight(&c.name) {
                     continue;
                 }
+                // Throttled: first pass after the container appears, then
+                // hourly — not on every 30s tick (see ownership_sweep_due).
+                if !ownership_sweep_due(&c.name) {
+                    continue;
+                }
                 if ensure_running_container_ownership(&c.name).await {
                     tracing::info!(container = %c.name, "volume ownership repaired during reconcile — restarting to recover");
                     let _ = tokio::process::Command::new("podman")

image-recipe/_archived/build-auto-installer-iso.sh

@@ -254,8 +254,17 @@ container_pull() {
 echo "📦 Step 1: Building root filesystem..."
 
 ROOTFS_TAR="$WORK_DIR/archipelago-rootfs.tar"
+ROOTFS_STAMP="$WORK_DIR/archipelago-rootfs.recipe.sha256"
 
-if [ ! -f "$ROOTFS_TAR" ] || [ "$1" == "--rebuild" ]; then
+# The cached rootfs must be invalidated when its recipe changes: a stale
+# archipelago-rootfs.tar on the build machine shipped ISOs with NO
+# wpasupplicant/iw/rfkill (WiFi dead on laptops) long after those packages
+# were added to the Dockerfile below — the cache condition never looked at
+# the recipe. Hash the rootfs-defining region of this script; any edit to it
+# forces a rebuild. `--rebuild` still forces one unconditionally.
+RECIPE_HASH=$(sed -n '/^# STEP 1: Build complete root filesystem/,/^# STEP 2: Build minimal installer/p' "$0" | sha256sum | cut -d' ' -f1)
+
+if [ ! -f "$ROOTFS_TAR" ] || [ "${1:-}" == "--rebuild" ] || [ "$(cat "$ROOTFS_STAMP" 2>/dev/null)" != "$RECIPE_HASH" ]; then
     echo "   Using Docker to create Debian root filesystem..."
     
     # Create a Dockerfile for building the rootfs
@@ -694,6 +703,7 @@ SYSTEMDSERVICE
     $CONTAINER_CMD export archipelago-rootfs-tmp > "$ROOTFS_TAR"
     $CONTAINER_CMD rm archipelago-rootfs-tmp
     
+    echo "$RECIPE_HASH" > "$ROOTFS_STAMP"
     echo "✅ Root filesystem created: $(du -h "$ROOTFS_TAR" | cut -f1)"
 else
     echo "✅ Using cached root filesystem: $(du -h "$ROOTFS_TAR" | cut -f1)"
@@ -1218,6 +1228,23 @@ else
     echo "   ⚠  nostr-rs-relay image not available — relay binary will be missing"
 fi
 
+# A missing nvpn/nostr-rs-relay used to be a warning, and the resulting ISO
+# shipped units that crash-looped (or silently lacked VPN signaling) on every
+# install. Refuse to produce that ISO unless explicitly overridden.
+MISSING_VPN_BINARIES=""
+[ -f "$ARCH_DIR/bin/nvpn" ] || MISSING_VPN_BINARIES="$MISSING_VPN_BINARIES nvpn"
+[ -f "$ARCH_DIR/bin/nostr-rs-relay" ] || MISSING_VPN_BINARIES="$MISSING_VPN_BINARIES nostr-rs-relay"
+if [ -n "$MISSING_VPN_BINARIES" ]; then
+    if [ "${ALLOW_MISSING_VPN_BINARIES:-0}" = "1" ]; then
+        echo "   ⚠  Building WITHOUT:$MISSING_VPN_BINARIES (ALLOW_MISSING_VPN_BINARIES=1)"
+    else
+        echo "   ❌ Required binaries not extracted:$MISSING_VPN_BINARIES"
+        echo "      The registry (146.59.87.168:3000) must be reachable and hold the images,"
+        echo "      or set ALLOW_MISSING_VPN_BINARIES=1 to ship without VPN signaling."
+        exit 1
+    fi
+fi
+
 # Copy WireGuard helper script
 if [ -f "$WORK_DIR/archipelago-wg" ]; then
     cp "$WORK_DIR/archipelago-wg" "$ARCH_DIR/bin/archipelago-wg"
@@ -3328,6 +3355,11 @@ echo ""
 echo "=== Done ==="
 DIAGSCRIPT
 chmod +x /mnt/target/opt/archipelago/scripts/first-boot-diag.sh
+# v1.7.104 shipped installs where this script was missing while its unit was
+# enabled (203/EXEC forever). Verify the write actually landed, loudly.
+if [ ! -x /mnt/target/opt/archipelago/scripts/first-boot-diag.sh ]; then
+    echo "ERROR: first-boot-diag.sh was not written to the target" >&2
+fi
 
 # Systemd oneshot service for first-boot diagnostics
 cat > /mnt/target/etc/systemd/system/archipelago-diag.service <<'DIAGSVC'
@@ -3335,6 +3367,8 @@ cat > /mnt/target/etc/systemd/system/archipelago-diag.service <<'DIAGSVC'
 Description=Archipelago First Boot Diagnostics
 After=multi-user.target archipelago.service nginx.service
 ConditionPathExists=!/var/log/archipelago-first-boot-diag.log
+# Skip cleanly (instead of failing 203/EXEC) if the script is missing.
+ConditionPathExists=/opt/archipelago/scripts/first-boot-diag.sh
 
 [Service]
 Type=oneshot

image-recipe/configs/nostr-relay.service

@@ -3,6 +3,9 @@ Description=Archipelago Private Nostr Relay
 After=network-online.target
 Wants=network-online.target
 Before=nostr-vpn.service
+# An ISO built without the relay binary (registry unreachable at build time)
+# must not crash-loop every 3s forever — skip cleanly instead.
+ConditionPathExists=/usr/local/bin/nostr-rs-relay
 
 [Service]
 Type=simple

image-recipe/configs/nostr-vpn.service

@@ -4,6 +4,9 @@ After=network-online.target tor.service archipelago.service
 Wants=network-online.target
 StartLimitIntervalSec=300
 StartLimitBurst=10
+# An ISO built without the nvpn binary (registry unreachable at build time)
+# must not restart-loop — skip cleanly instead.
+ConditionPathExists=/usr/local/bin/nvpn
 
 [Service]
 Type=simple

neode-ui/src/App.vue

@@ -424,10 +424,14 @@ onMounted(async () => {
   const { IS_DEMO } = await import('@/composables/useDemoIntro')
   if (IS_DEMO && bootPath === '/') replayRequested = true
   let onboardingComplete: boolean | null = localStorage.getItem('neode_onboarding_complete') === '1' ? true : null
-  const splashCandidate = !seenIntro
-    && (fromBoot || (bootPath === '/' && import.meta.env.VITE_DEV_MODE !== 'boot'))
+  // Root boots always ask the backend — even when this browser thinks it has
+  // seen the intro. Both `neode_intro_seen` and `neode_onboarding_complete`
+  // are per-origin browser state: after a reinstall (or another node coming
+  // up on a DHCP-recycled IP) they describe the PREVIOUS node and would mute
+  // a fresh install's intro / misroute it to login.
+  const splashCandidate = fromBoot || (bootPath === '/' && import.meta.env.VITE_DEV_MODE !== 'boot')
 
-  if (splashCandidate && onboardingComplete !== true) {
+  if (splashCandidate) {
     try {
       const { checkOnboardingStatus } = await import('@/composables/useOnboarding')
       // Bound the pre-splash status check: its retry ladder can spend ~30s
@@ -437,10 +441,17 @@ onMounted(async () => {
       // the splash play (a fresh install IS the slow-backend case; onboarded
       // nodes answer in milliseconds, so their suppression path is intact).
       // handleSplashComplete re-checks with full retries after the intro.
-      onboardingComplete = await Promise.race([
+      const live = await Promise.race([
         checkOnboardingStatus(),
         new Promise<null>((resolve) => setTimeout(() => resolve(null), 2500)),
       ])
+      if (live !== null) onboardingComplete = live
+      if (live === false && seenIntro) {
+        // Backend-confirmed fresh node behind a browser with a stale flag —
+        // drop it so this boot (and every later one) plays the intro.
+        try { localStorage.removeItem('neode_intro_seen') } catch { /* noop */ }
+        seenIntro = false
+      }
     } catch {
       onboardingComplete = localStorage.getItem('neode_onboarding_complete') === '1' ? true : null
     }

neode-ui/src/components/CompanionIntroOverlay.vue

@@ -161,6 +161,14 @@
                 </div>
               </div>
               <p v-if="wgError" class="text-xs text-red-400 text-center mb-3">{{ wgError }}</p>
+              <button
+                v-if="wgError && !wgLoading"
+                type="button"
+                class="inline-flex w-full items-center justify-center rounded-lg bg-white/5 border border-white/15 px-4 py-2.5 text-sm font-medium text-white/80 hover:bg-white/10 hover:text-white transition-colors mb-3"
+                @click="retryWgPeer"
+              >
+                Try again
+              </button>
 
               <!-- Same-device path: a phone can't scan its own screen, so offer
                    the config as a file WireGuard can import. -->
@@ -318,7 +326,15 @@ const POST_INTRO_GRACE_MS = 2000
 
 let calmTicker: ReturnType<typeof setInterval> | null = null
 
+// Running inside the companion app's own WebView (it injects this JS bridge).
+// The "get the companion app" pitch is nonsense there — the user is already in
+// it — and the WG steps mid-pairing race the phone's changing network (the
+// "Failed to fetch" dead-end QR). Server/tunnel management for connected
+// companions lives in the NESMenu instead.
+const IN_COMPANION_APP = typeof (window as { ArchipelagoNative?: unknown }).ArchipelagoNative !== 'undefined'
+
 onMounted(() => {
+  if (IN_COMPANION_APP) return
   try {
     if (localStorage.getItem(STORAGE_KEY) !== '1') {
       setTimeout(maybeShow, BASE_DELAY_MS)
@@ -471,6 +487,19 @@ function backFromPair() {
   }
 }
 
+// Network-class failures: the node itself was unreachable (as opposed to the
+// backend answering with an RPC error). Includes the client's own timeout.
+const WG_NETWORK_ERR = /failed to fetch|networkerror|load failed|abort|request timeout/i
+
+// Auto-retry ladder for network-class failures. On a first install this step
+// is often reached while the backend is still settling (services starting,
+// backend restarting during container orchestration) — a single failed fetch
+// left a permanently blank QR unless the user spotted the retry button.
+const WG_RETRY_DELAYS_MS = [2000, 4000, 8000]
+
+const sleep = (ms: number) => new Promise<void>((resolve) => setTimeout(resolve, ms))
+const stillOnWgStep = () => visible.value && step.value === 'wgqr'
+
 // Create (or fetch) the phone's VPN peer and render its config as a QR.
 // Reuses the same RPCs as the Server page's Add Device modal; the peer is
 // looked up first so reopening the modal never duplicates it.
@@ -478,30 +507,70 @@ async function loadWgPeer() {
   if (wgQrDataUrl.value || wgLoading.value) return
   wgLoading.value = true
   wgError.value = ''
-  try {
-    const listed = await rpcClient
-      .call<{ peers: { name: string }[] }>({ method: 'vpn.list-peers' })
-      .catch(() => ({ peers: [] as { name: string }[] }))
-    const exists = (listed.peers || []).some((p) => p.name === WG_PEER_NAME)
-    const res = await rpcClient.call<{ config: string; peer_ip: string }>({
-      method: exists ? 'vpn.peer-config' : 'vpn.create-peer',
-      params: { name: WG_PEER_NAME },
-    })
-    wgConfig.value = res.config
-    wgQrDataUrl.value = await QRCode.toDataURL(res.config, {
-      width: 512,
-      margin: 3,
-      errorCorrectionLevel: 'M',
-      color: {
-        dark: '#111111',
-        light: '#ffffff',
-      },
-    })
-  } catch (e) {
-    wgError.value = e instanceof Error ? e.message : 'Failed to generate the tunnel config'
-  } finally {
-    wgLoading.value = false
+  for (let attempt = 0; ; attempt++) {
+    try {
+      await provisionWgPeer()
+      break
+    } catch (e) {
+      const raw = e instanceof Error ? e.message : ''
+      const isNetworkErr = WG_NETWORK_ERR.test(raw)
+      if (isNetworkErr && attempt < WG_RETRY_DELAYS_MS.length && stillOnWgStep()) {
+        await sleep(WG_RETRY_DELAYS_MS[attempt])
+        if (stillOnWgStep()) continue
+      }
+      // fetch()'s raw "Failed to fetch" means the node itself was unreachable —
+      // after the retry ladder that's usually the phone's network mid-change
+      // (WiFi drop, or a half-configured tunnel already routing 10.44.0.0/16).
+      // Say so, and leave a Retry path instead of a dead end.
+      wgError.value = isNetworkErr
+        ? "Can't reach your node. Check the phone is on the same network as the node (and any half-set-up tunnel is switched off), then tap Try again."
+        : raw || 'Failed to generate the tunnel config'
+      break
+    }
   }
+  wgLoading.value = false
+}
+
+async function provisionWgPeer() {
+  const listed = await rpcClient
+    .call<{ peers: { name: string }[] }>({ method: 'vpn.list-peers' })
+    .catch(() => null)
+  // list-peers unreachable → don't guess "doesn't exist": create-peer on an
+  // existing name would fail. Try create first, fall back to peer-config.
+  const exists = listed === null
+    ? null
+    : (listed.peers || []).some((p) => p.name === WG_PEER_NAME)
+  let res: { config: string; peer_ip: string }
+  if (exists === true) {
+    res = await rpcClient.call({ method: 'vpn.peer-config', params: { name: WG_PEER_NAME } })
+  } else {
+    try {
+      res = await rpcClient.call({ method: 'vpn.create-peer', params: { name: WG_PEER_NAME } })
+    } catch (e) {
+      // Peer already provisioned on a previous visit (list failed or raced).
+      const msg = e instanceof Error ? e.message : ''
+      if (/exist|duplicate/i.test(msg)) {
+        res = await rpcClient.call({ method: 'vpn.peer-config', params: { name: WG_PEER_NAME } })
+      } else {
+        throw e
+      }
+    }
+  }
+  wgConfig.value = res.config
+  wgQrDataUrl.value = await QRCode.toDataURL(res.config, {
+    width: 512,
+    margin: 3,
+    errorCorrectionLevel: 'M',
+    color: {
+      dark: '#111111',
+      light: '#ffffff',
+    },
+  })
+}
+
+function retryWgPeer() {
+  wgError.value = ''
+  void loadWgPeer()
 }
 
 // Same-device path: hand the config to the WireGuard app as an importable

neode-ui/src/utils/__tests__/introSplash.test.ts

@@ -38,4 +38,50 @@ describe('shouldShowIntroSplash', () => {
       replayRequested: true,
     })).toBe(true)
   })
+
+  it('a confirmed-fresh node plays the intro despite a stale per-origin seenIntro flag (reinstall / DHCP-recycled IP)', () => {
+    expect(shouldShowIntroSplash({
+      seenIntro: true,
+      routePath: '/',
+      fromBoot: false,
+      onboardingComplete: false,
+    })).toBe(true)
+  })
+
+  it('a confirmed-fresh node plays the intro on the boot-screen handoff too', () => {
+    expect(shouldShowIntroSplash({
+      seenIntro: true,
+      routePath: '/login',
+      fromBoot: true,
+      onboardingComplete: false,
+    })).toBe(true)
+  })
+
+  it('stale seenIntro still suppresses when the backend answer is unknown', () => {
+    expect(shouldShowIntroSplash({
+      seenIntro: true,
+      routePath: '/',
+      fromBoot: false,
+      onboardingComplete: null,
+    })).toBe(false)
+  })
+
+  it('fresh node on a deep route without boot handoff stays suppressed', () => {
+    expect(shouldShowIntroSplash({
+      seenIntro: false,
+      routePath: '/onboarding/seed',
+      fromBoot: false,
+      onboardingComplete: false,
+    })).toBe(false)
+  })
+
+  it('boot dev mode never root-boots into the intro', () => {
+    expect(shouldShowIntroSplash({
+      seenIntro: false,
+      routePath: '/',
+      fromBoot: false,
+      devMode: 'boot',
+      onboardingComplete: false,
+    })).toBe(false)
+  })
 })

neode-ui/src/utils/introSplash.ts

@@ -10,10 +10,19 @@ export interface IntroSplashDecisionInput {
 
 export function shouldShowIntroSplash(input: IntroSplashDecisionInput): boolean {
   if (input.replayRequested) return true
+
+  const isDirectRoute = input.routePath !== '/'
+  // A node the backend CONFIRMS has never completed onboarding always gets
+  // the full intro on a root boot. `seenIntro` is per-origin browser state —
+  // after a reinstall (or a DHCP-recycled IP), the browser still carries the
+  // previous node's flag at the same origin, which silently muted the intro
+  // on genuinely fresh installs.
+  if (input.onboardingComplete === false && (input.fromBoot || (!isDirectRoute && input.devMode !== 'boot'))) {
+    return true
+  }
   if (input.seenIntro) return false
   if (input.onboardingComplete === true) return false
 
-  const isDirectRoute = input.routePath !== '/'
   if (input.fromBoot) return true
   if (input.devMode === 'boot') return false
   return !isDirectRoute

neode-ui/src/views/OnboardingWrapper.vue

@@ -691,20 +691,24 @@ video.bg-layer {
    why the kiosk login/onboarding background still went black. Keep 2D
    opacity crossfades; drop 3D transforms, blur filters, and blend-mode
    glitch overlays. */
-:global(html.kiosk-mode) .bg-perspective-container,
-:global(html.kiosk-mode) .perspective-container {
+/* The full selector must live inside :global() — with `:global(html.kiosk-mode)
+   .bg-layer` the SFC compiler drops the descendant part, emitting bare
+   `html.kiosk-mode { display: none !important }` rules that blank the whole
+   document on kiosk (the v1.7.104 white-screen). */
+:global(html.kiosk-mode .bg-perspective-container),
+:global(html.kiosk-mode .perspective-container) {
   perspective: none !important;
 }
-:global(html.kiosk-mode) .bg-layer,
-:global(html.kiosk-mode) .view-wrapper {
+:global(html.kiosk-mode .bg-layer),
+:global(html.kiosk-mode .view-wrapper) {
   transform: none !important;
   transform-style: flat !important;
   backface-visibility: visible !important;
   will-change: auto !important;
   filter: none !important;
 }
-:global(html.kiosk-mode) .login-glitch-layer,
-:global(html.kiosk-mode) .login-glitch-scan {
+:global(html.kiosk-mode .login-glitch-layer),
+:global(html.kiosk-mode .login-glitch-scan) {
   display: none !important;
 }
 </style>

scripts/run-post-install-tests.sh

@@ -103,6 +103,23 @@ for f in /usr/local/bin/archipelago \
   fi
 done
 
+# 1.1b — Every enabled archipelago/nostr unit must have an existing ExecStart
+# payload. v1.7.104 shipped nostr-relay.service without its binary (3s
+# crash-loop forever) and archipelago-diag.service without its script
+# (203/EXEC) — catch that class of ISO defect on first boot, by generic rule.
+for unit in /etc/systemd/system/archipelago*.service /etc/systemd/system/nostr*.service; do
+  [ -f "$unit" ] || continue
+  systemctl is-enabled "$(basename "$unit")" >/dev/null 2>&1 || continue
+  exec_bin=$(grep -m1 '^ExecStart=' "$unit" | sed 's/^ExecStart=[-+@!:]*//' | awk '{print $1}')
+  case "$exec_bin" in
+    /*) if [ -e "$exec_bin" ]; then
+          pass "Unit payload exists: $(basename "$unit") → $exec_bin"
+        else
+          fail "Unit payload missing" "$(basename "$unit") → $exec_bin"
+        fi ;;
+  esac
+done
+
 # 1.2 — Critical services active
 for svc in archipelago nginx; do
   if systemctl is-active "$svc" >/dev/null 2>&1; then