deploy: feature flags, --diff, tolerate failed restarts

Li3, NVMe watchdog, Home Assistant/ESPHome, Frigate and Cockpit are
installed, enabled and restarted only when their ENABLE_* flag is 1.
--diff shows what would change in /etc. A unit that fails to restart is
recorded as a warning instead of aborting the deploy.

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

deploy.sh

@@ -105,6 +105,17 @@ case "${1:-}" in
         rm -f "$tmp"
         [ "$rc" -eq 0 ] && echo "check OK: $(template_files | wc -l) templates render cleanly"
         exit "$rc" ;;
+    --diff)     # ./deploy.sh --diff [conf] — what would change in /etc, without installing
+        load_conf "${2:-$VANLINK_CONF}"
+        grep -E '^[[:space:]]*install_rendered +[^" ]+ +/' deploy.sh | while read -r _ src dst _; do
+            if [ ! -e "$dst" ]; then
+                echo "NEW      $dst"
+            elif ! diff -q <(render "$src") "$dst" >/dev/null; then
+                echo "CHANGED  $dst"
+                diff -u "$dst" <(render "$src") | sed 's/^/    /' || true
+            fi
+        done
+        exit 0 ;;
     render)
         [ -n "${2:-}" ] || { echo "Usage: $0 render <file>"; exit 1; }
         load_conf "$VANLINK_CONF"
@@ -135,8 +146,10 @@ REQUIRED_PACKAGES=(
     python3-paho-mqtt
     mobile-broadband-provider-info
     zerotier-one
-    podman
 )
+if [ "$ENABLE_HA" = 1 ]; then
+    REQUIRED_PACKAGES+=(podman)
+fi
 OPTIONAL_PACKAGES=(
 )
 for pkg in "${REQUIRED_PACKAGES[@]}"; do
@@ -175,6 +188,12 @@ write_warnings() {
     } > "$WARNINGS_FILE"
 }
 
+# A host file with uncommitted edits means this deploy uses unreviewed values.
+conf_real=$(readlink -f "$VANLINK_CONF")
+if git -c safe.directory='*' -C "$(dirname "$conf_real")" status --porcelain -- "$conf_real" 2>/dev/null | grep -q .; then
+    warn "$conf_real has uncommitted changes — commit it so the host config stays reviewable"
+fi
+
 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
@@ -321,7 +340,6 @@ python3 -c 'import paho.mqtt' 2>/dev/null \
 install -D -m0644 router-status/mosquitto-listener.conf /etc/mosquitto/conf.d/van-listener.conf
 # Restart limit drop-ins: prevent infinite restart loops that trigger hardware watchdog
 install -D -m0644 router-status/van-gps-owntracks-restart-limit.conf /etc/systemd/system/van-gps-owntracks.service.d/restart-limit.conf
-install -D -m0644 li3/van-li3-battery-restart-limit.conf /etc/systemd/system/van-li3-battery.service.d/restart-limit.conf
 
 echo "== gps (cellular modem GNSS -> gpsd) =="
 if dpkg -s gpsd >/dev/null 2>&1; then
@@ -344,6 +362,7 @@ python3 -c 'import gps' 2>/dev/null \
 python3 -c 'import paho.mqtt' 2>/dev/null \
     || warn "python3-paho-mqtt missing (apt install python3-paho-mqtt) — van-gps-owntracks won't start"
 
+if [ "$ENABLE_LI3" = 1 ]; then
     echo "== li3 (RV house battery BMS -> MQTT/HA) =="
     # NOT the laptop's own AC/battery monitor — that's power/van-battery (different
     # hardware, different concern). This is the Lithionics Li3 12V LiFePO4 house
@@ -352,12 +371,14 @@ echo "== li3 (RV house battery BMS -> MQTT/HA) =="
     # li3/config.json.example — same pattern as gps/pushover).
     install -D -m0755 li3/van-li3-battery         /usr/local/sbin/van-li3-battery
     install -D -m0644 li3/van-li3-battery.service /etc/systemd/system/van-li3-battery.service
+    install -D -m0644 li3/van-li3-battery-restart-limit.conf /etc/systemd/system/van-li3-battery.service.d/restart-limit.conf
     if [ ! -f /etc/van-li3/config.json ]; then
         install -D -m0600 li3/config.json.example /etc/van-li3/config.json
         warn "seeded /etc/van-li3/config.json (EDIT IT: add MQTT username + password)"
     fi
     python3 -c 'import bleak' 2>/dev/null \
         || warn "python3-bleak missing (apt install python3-bleak) — van-li3-battery won't start"
+fi
 
 echo "== thermal monitor =="
 install -D -m0755 power/van-thermal         /usr/local/sbin/van-thermal
@@ -370,24 +391,30 @@ if [ ! -f /etc/van-battery/pushover.json ]; then
     warn "seeded /etc/van-battery/pushover.json (EDIT IT: add Pushover token + user)"
 fi
 
+if [ "$ENABLE_NVME_WATCH" = 1 ]; then
     echo "== nvme watchdog =="
     install -D -m0755 power/van-nvme-watch         /usr/local/sbin/van-nvme-watch
     install_rendered power/nvme-watch-config.json  /etc/van-nvme-watch/config.json
     install -D -m0644 power/van-nvme-watch.service /etc/systemd/system/van-nvme-watch.service
+fi
 
 echo "== home assistant =="
 # Native HA (Podman Quadlet, replaced the ha_van VM). daemon-reload below
 # regenerates homeassistant.service; started (not restarted) at the end so a
 # deploy never bounces HA — after editing the .container, restart it manually.
+if [ "$ENABLE_HA" = 1 ]; then
     install -D -m0644 ha/homeassistant.container /etc/containers/systemd/homeassistant.container
     install -d -m0755 /srv/homeassistant
     # ESPHome dashboard (sibling container, same rationale as HA above — no
     # Supervisor/add-on store here).
     install -D -m0644 ha/esphome.container /etc/containers/systemd/esphome.container
     install -d -m0755 /srv/esphome
+fi
 # Frigate NVR (sibling container, same rationale as HA/ESPHome above).
+if [ "$ENABLE_FRIGATE" = 1 ]; then
     install -D -m0644 ha/frigate.container /etc/containers/systemd/frigate.container
     install -d -m0755 /srv/frigate/config /srv/frigate/storage
+fi
 
 echo "== hardware watchdog =="
 install -D -m0644 power/10-vanlink-watchdog.conf /etc/systemd/system.conf.d/10-vanlink-watchdog.conf
@@ -410,24 +437,41 @@ systemctl mask systemd-networkd-wait-online.service >/dev/null 2>&1 || true
 systemctl unmask hostapd >/dev/null 2>&1 || true
 # Disable system dnsmasq.service to avoid port 53 conflicts — van-ap-dnsmasq owns AP DHCP
 systemctl disable dnsmasq.service >/dev/null 2>&1 || true
-systemctl enable regdomain.service van-br0-setup.service hostapd hostapd-2g van-ap-dnsmasq nftables systemd-networkd van-failover van-thermal van-nvme-watch van-ap-watchdog van-ap-watchdog-2g van-wlan-watchdog van-modem-watch van-sms-watch van-gps-owntracks van-li3-battery van-router-mqtt >/dev/null 2>&1 || true
+ENABLE_UNITS=(regdomain.service van-br0-setup.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-modem-watch van-sms-watch van-gps-owntracks van-router-mqtt)
+if [ "$ENABLE_NVME_WATCH" = 1 ]; then
+    ENABLE_UNITS+=(van-nvme-watch)
+fi
+if [ "$ENABLE_LI3" = 1 ]; then
+    ENABLE_UNITS+=(van-li3-battery)
+fi
+systemctl enable "${ENABLE_UNITS[@]}" >/dev/null 2>&1 || true
 # bluetooth: host BlueZ serves the onboard hci0 to the HA container over D-Bus
 systemctl enable --now bluetooth >/dev/null 2>&1 || true
+if [ "$ENABLE_HA" = 1 ]; then
     systemctl start homeassistant || warn "homeassistant failed to start (podman/quadlet — check journalctl -u homeassistant)"
     systemctl start esphome || warn "esphome failed to start (podman/quadlet — check journalctl -u esphome)"
+fi
+if [ "$ENABLE_FRIGATE" = 1 ]; then
     systemctl start frigate || warn "frigate failed to start (podman/quadlet — check journalctl -u frigate)"
+fi
 systemctl restart van-thermal
+if [ "$ENABLE_NVME_WATCH" = 1 ]; then
     systemctl restart van-nvme-watch
+fi
 systemctl restart van-sms-watch
 systemctl restart van-gps-owntracks
+if [ "$ENABLE_LI3" = 1 ]; then
     systemctl restart van-li3-battery
+fi
 systemctl restart van-router-mqtt
 # Pick up unmanaged-devices changes so NM releases/keeps the right interfaces.
 nmcli general reload 2>/dev/null || systemctl reload NetworkManager 2>/dev/null || true
 # restart in dependency order: bridge + members first, then hostapd enslaves the
 # radios, then dnsmasq binds br0, then NAT/failover
 systemctl restart systemd-networkd
-systemctl restart van-ap-dnsmasq nftables van-failover van-wlan-watchdog
+for u in van-ap-dnsmasq nftables van-failover van-wlan-watchdog; do
+    systemctl restart "$u" || warn "$u failed to restart (journalctl -xeu $u)"
+done
 # 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 \

tests/check-templates.sh

@@ -69,4 +69,32 @@ else
     ok "van: unmanaged-devices has no eth0"
 fi
 
+# 6. flagged units/paths only appear inside their ENABLE_* guard in deploy.sh.
+#    Convention: guards are column-0 `if [ "$ENABLE_X" = 1 ]; then` ... `fi`,
+#    contents indented (so a nested `fi` never sits in column 0).
+if awk '
+    BEGIN {
+        need["van-li3-battery"]="ENABLE_LI3"
+        need["van-nvme-watch"]="ENABLE_NVME_WATCH"
+        need["nvme-watch-config"]="ENABLE_NVME_WATCH"
+        need["homeassistant"]="ENABLE_HA"
+        need["esphome"]="ENABLE_HA"
+        need["frigate"]="ENABLE_FRIGATE"
+        need["cockpit"]="ENABLE_COCKPIT"
+    }
+    /^if \[ "\$ENABLE_[A-Z0-9_]+" = 1 \]/ { match($0, /ENABLE_[A-Z0-9_]+/); guard=substr($0, RSTART, RLENGTH); next }
+    /^fi([[:space:]]|$)/                  { guard=""; next }
+    /^[[:space:]]*(#|echo)/               { next }
+    { for (u in need) if (index($0, u) && guard != need[u]) {
+          printf "       deploy.sh:%d mentions %s outside an %s guard: %s\n", NR, u, need[u], $0; bad=1 } }
+    END { exit bad }
+' deploy.sh; then ok "flagged units are only touched inside their ENABLE_* guard"; else bad "flag gating"; fi
+
+# 8. ./deploy.sh --diff runs (no root) and lists rendered files
+if out=$(./deploy.sh --diff hosts/van.conf 2>&1) && echo "$out" | grep -qE '^(NEW|CHANGED) '; then
+    ok "deploy.sh --diff hosts/van.conf"
+else
+    bad "deploy.sh --diff hosts/van.conf"; echo "$out" | sed 's/^/       /'
+fi
+
 exit "$fail"