fix(iso): fail builds on missing VPN binaries, skip units cleanly, invalidate stale rootfs cache

v1.7.104 shipped ISOs whose units crash-looped (nostr-relay 3s loop,
archipelago-diag 203/EXEC) because build-time extraction failures were mere
warnings and the cached rootfs never tracked its recipe:

- hash the rootfs-defining region of the build script and rebuild when it
  changes (stale cache shipped ISOs without wpasupplicant/iw/rfkill)
- refuse to build without nvpn / nostr-rs-relay unless
  ALLOW_MISSING_VPN_BINARIES=1
- ConditionPathExists on nostr-relay/nostr-vpn/diag units so a stripped
  image skips them instead of crash-looping
- post-install test: every enabled archipelago*/nostr* unit must have an
  existing ExecStart payload

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

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"
@@ -3345,6 +3372,11 @@ 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'
@@ -3352,6 +3384,8 @@ 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

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