deploy: --apply-network with detached apply, connectivity gate and automatic rollback

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KqhjP7nud5gdBg25zCiRk9

deploy.sh

@@ -11,6 +11,8 @@
 #         ./deploy.sh --classify-radio     # reads `iw dev <if> info` text on stdin, prints beaconing|silent (no ssid line = silent; used by post_check; for tests)
 #         ./deploy.sh --render-wan-netplan # rendered /etc/netplan/50-van-wan.yaml (ethernet part + wifis stanza when WIFI_WAN_IFACE is set)
 #         ./deploy.sh --wan-plan [conf]    # what the NetworkManager WAN provisioning would do (read-only, no root)
+#         ./deploy.sh --apply-network      # root: install the WAN netplan, apply it from a detached unit, roll back automatically if the uplink does not return
+#         ./deploy.sh --print-apply-helper [conf]  # print the detached apply/rollback helper script (read-only, no root; for review and tests)
 #         ./deploy.sh render <file>        # preview a templated file on stdout
 #         ./deploy.sh --redact             # filter stdin, masking secret values (used by --diff; for tests)
 #         VANLINK_NM_DIR=<dir>             # test override: where existing NM *.nmconnection files are looked up (default /etc/NetworkManager/system-connections)
@@ -275,6 +277,70 @@ post_check() {  # read-only live checks; every probe is guarded, warns instead o
     else warn "post-deploy: default route present but 1.1.1.1 does not answer ping"; fi
 }
 
+apply_helper_script() {  # apply_helper_script <backup-dir> — the script the detached unit runs
+    local bak=$1
+    # Unquoted heredoc on purpose: $bak and $STARLINK_IFACE expand now; \$... stay for run time.
+    cat <<HELPER
+#!/bin/bash
+# Generated by deploy.sh --apply-network: apply the WAN netplan, verify the uplink, roll back if it did not come back.
+exec >>/var/log/vanlink-apply-network.log 2>&1
+echo "== apply-network \$(date -Is) (backup: $bak)"
+netplan generate && netplan apply || echo "netplan apply failed"
+ok=0
+for i in \$(seq 1 60); do
+    have_default=0; ip route show default | grep . >/dev/null && have_default=1
+    nm_ok=1
+    if [ -e /sys/class/net/$STARLINK_IFACE ]; then
+        nm_ok=0
+        nmcli -t -f DEVICE,STATE device 2>/dev/null | grep -Fx '$STARLINK_IFACE:connected' >/dev/null && nm_ok=1
+    fi
+    if [ \$have_default = 1 ] && [ \$nm_ok = 1 ] && ping -c1 -W2 1.1.1.1 >/dev/null 2>&1; then ok=1; break; fi
+    sleep 1
+done
+if [ \$ok = 1 ]; then
+    echo "apply-network OK"
+else
+    echo "apply-network FAILED — restoring $bak"
+    rm -f /etc/netplan/*
+    cp -a $bak/. /etc/netplan/
+    netplan generate && netplan apply
+    echo "apply-network ROLLED BACK"
+    exit 1
+fi
+HELPER
+}
+
+apply_network() {  # ./deploy.sh --apply-network — explicit, root; see spec §4
+    [ "$(id -u)" = 0 ] || die "--apply-network needs root (sudo)"
+    [ "$ENABLE_NM_WAN" = 1 ] || die "ENABLE_NM_WAN is 0 in $VANLINK_CONF — nothing to apply"
+    dpkg -s network-manager >/dev/null 2>&1 || die "network-manager is not installed — run ./deploy.sh first"
+    local stamp bak tmp
+    stamp=$(date +%Y%m%d-%H%M%S)
+    bak=/var/backups/vanlink-netplan-$stamp
+    install -d -m0700 "$bak"
+    cp -a /etc/netplan/. "$bak/"
+    tmp=$(mktemp)
+    render_wan_netplan > "$tmp"
+    check_rendered ap/50-van-wan.yaml "$tmp" || { rm -f "$tmp"; exit 1; }
+    install -m0600 "$tmp" /etc/netplan/50-van-wan.yaml
+    rm -f "$tmp"
+    if [ -f /etc/netplan/10-dhcp-all-interfaces.yaml ]; then
+        mv /etc/netplan/10-dhcp-all-interfaces.yaml /etc/netplan/10-dhcp-all-interfaces.yaml.vanlink-disabled
+    fi
+    : > /var/log/vanlink-apply-network.log
+    apply_helper_script "$bak" > /run/vanlink-apply-network.sh
+    chmod 0700 /run/vanlink-apply-network.sh
+    echo "backup: $bak   log: /var/log/vanlink-apply-network.log"
+    echo "applying from a detached unit (survives an SSH drop); waiting up to 90 s ..."
+    systemctl reset-failed vanlink-apply-network 2>/dev/null || true
+    systemd-run --unit=vanlink-apply-network --collect /bin/bash /run/vanlink-apply-network.sh >/dev/null
+    local t=0
+    while systemctl is-active --quiet vanlink-apply-network && [ "$t" -lt 90 ]; do sleep 1; t=$((t + 1)); done
+    tail -n 6 /var/log/vanlink-apply-network.log 2>/dev/null || true
+    grep -q 'apply-network OK' /var/log/vanlink-apply-network.log 2>/dev/null \
+        || die "apply-network did not report OK — see /var/log/vanlink-apply-network.log (previous config: $bak)"
+}
+
 case "${1:-}" in
     --templates)
         template_files
@@ -320,6 +386,14 @@ case "${1:-}" in
     --redact)   # ./deploy.sh --redact — stdin through redact_secrets (no config, no root)
         redact_secrets
         exit 0 ;;
+    --apply-network)  # ./deploy.sh --apply-network — root; applies the WAN netplan with automatic rollback
+        load_conf "$VANLINK_CONF"
+        apply_network
+        exit 0 ;;
+    --print-apply-helper)  # for review/tests: the helper script, with a placeholder backup dir; no root, no changes
+        load_conf "${2:-$VANLINK_CONF}"
+        apply_helper_script /var/backups/vanlink-netplan-EXAMPLE
+        exit 0 ;;
     --render-wan-netplan) load_conf "$VANLINK_CONF"; render_wan_netplan; exit 0 ;;
     --wan-plan)  # ./deploy.sh --wan-plan [conf] — what the NM WAN provisioning would do; changes nothing
         load_conf "${2:-$VANLINK_CONF}"

tests/check-templates.sh

@@ -257,4 +257,16 @@ rm -rf "$nmd" "$nme"
 # 17c. NM must not auto-create "Wired connection" profiles
 [ "$(grep -v '^[[:space:]]*#' ap/nm-no-auto-default.conf 2>/dev/null | grep -v '^[[:space:]]*$')" = "$(printf '[main]\nno-auto-default=*')" ] && ok "nm-no-auto-default.conf is [main] + no-auto-default=*" || bad "ap/nm-no-auto-default.conf missing or wrong"
 
+# 18. the detached apply helper: syntax, ordering, rollback branch
+h=$(VANLINK_CONF=hosts/van.conf ./deploy.sh --print-apply-helper 2>&1) || { bad "--print-apply-helper failed"; echo "$h" | sed 's/^/       /'; h=; }
+if [ -n "$h" ]; then
+    echo "$h" | bash -n && ok "apply helper: bash -n" || bad "apply helper: bash -n"
+    echo "$h" | grep -q 'netplan generate' && echo "$h" | grep -q 'netplan apply' && ok "apply helper applies netplan" || bad "apply helper lacks netplan generate/apply"
+    echo "$h" | grep -q 'restoring' && ok "apply helper has a rollback branch" || bad "apply helper lacks rollback"
+    echo "$h" | grep -q 'enP2p33s0' && ok "apply helper waits on the Starlink port" || bad "apply helper does not reference STARLINK_IFACE"
+    # rollback must come after the wait loop, and the backup is restored wholesale
+    a=$(echo "$h" | grep -n 'netplan apply' | head -1 | cut -d: -f1); r=$(echo "$h" | grep -n 'restoring' | head -1 | cut -d: -f1)
+    [ "$a" -lt "$r" ] && ok "apply helper: apply precedes rollback" || bad "apply helper: rollback ordering"
+fi
+
 exit "$fail"