signal-bot/scripts/install_service.sh

#!/bin/bash

# ============================================================================
# Install, start and verify the signal-bot user service.
#
# A *user* unit, not a system one: the bot runs as whoever registered the
# Signal account and reads that user's .env. Lingering is what makes it start
# at boot with nobody logged in -- without it, "survives reboots" is a lie the
# unit file cannot tell you about, so this script checks and fails loudly.
# ============================================================================

set -euo pipefail

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
readonly REPO_ROOT
SCRIPT_NAME="$(basename "$0")"
readonly SCRIPT_NAME
readonly UNIT_NAME="signal-bot.service"
readonly UNIT_DIR="${XDG_CONFIG_HOME:-$HOME/.config}/systemd/user"
readonly TEMPLATE="${REPO_ROOT}/scripts/${UNIT_NAME}"
readonly WATCHDOG_UNITS=("signal-api-watchdog.service" "signal-api-watchdog.timer")
readonly WATCHDOG_TIMER="signal-api-watchdog.timer"
readonly DEFAULT_PORT=8137

VERIFY_ONLY="false"

# shellcheck source=scripts/lib_signal.sh
source "${REPO_ROOT}/scripts/lib_signal.sh"

usage() {
	echo "Usage: $SCRIPT_NAME [--verify-only]"
	echo "  --verify-only   Check the running service without reinstalling it."
	exit 0
}

die() {
	echo "Error: $1" >&2
	exit 1
}

# The port the bot will actually bind: .env wins, code default otherwise.
bot_port() {
	local port=""
	if [[ -f "${REPO_ROOT}/.env" ]]; then
		port="$(sed -n 's/^BIND_PORT=[[:space:]]*//p' "${REPO_ROOT}/.env" | tail -1)"
	fi
	printf '%s' "${port:-$DEFAULT_PORT}"
}

# exiftool is what !add_photo strips uploads with, and the strip is not
# optional: without it every upload is refused rather than stored dirty.
# Installed here rather than documented, per the repo's own rule that a
# script owns its dependencies.
ensure_exiftool() {
	if ! command -v exiftool >/dev/null; then
		echo "Installing perl-image-exiftool (needed by !add_photo)..."
		if ! sudo pacman -S --needed --noconfirm perl-image-exiftool; then
			die "could not install perl-image-exiftool; run: sudo pacman -S perl-image-exiftool"
		fi
	fi
	# `command -v` answers for *this shell*, which is not who has to find it.
	# Arch installs to /usr/bin/vendor_perl, on an interactive PATH and not on
	# a systemd unit's -- so on 2026-08-31 the bot refused every upload while
	# exiftool sat plainly on the installer's PATH. Ask the bot's own resolver.
	if ! env -i "PATH=/usr/local/bin:/usr/bin" "${REPO_ROOT}/.venv/bin/python" -c \
		'import sys; from signal_bot.media_strip import locate; sys.exit(0 if locate() else 1)'; then
		die "exiftool is installed but signal_bot.media_strip.locate() cannot find it under the unit's PATH"
	fi
}

# ffmpeg drops the metadata *tracks* exiftool cannot see. An iPhone clip
# carries mebx timed-metadata holding per-frame face bounding boxes and a
# face id, and those survive a complete "-all= -time:all=" pass because they
# live in mdat as opaque samples, not as tags. Without ffmpeg every video is
# refused rather than stored with them.
ensure_ffmpeg() {
	if ! command -v ffmpeg >/dev/null || ! command -v ffprobe >/dev/null; then
		echo "Installing ffmpeg (needed to store video)..."
		if ! sudo pacman -S --needed --noconfirm ffmpeg; then
			die "could not install ffmpeg; run: sudo pacman -S ffmpeg"
		fi
	fi
	# Same trap as exiftool: ask the bot's own resolver, under the unit's PATH.
	if ! env -i "PATH=/usr/local/bin:/usr/bin" "${REPO_ROOT}/.venv/bin/python" -c \
		'import sys; from signal_bot.media_tracks import locate; sys.exit(0 if locate("ffmpeg") and locate("ffprobe") else 1)'; then
		die "ffmpeg is installed but signal_bot.media_tracks.locate() cannot find it under the unit's PATH"
	fi
}

# The management page is built, not committed: dist/ is a build output and
# this repository does not carry those. Verified by looking at the artefact
# rather than trusting the exit code, the same way exiftool is.
build_web() {
	local web="${REPO_ROOT}/web"
	if ! command -v pnpm >/dev/null; then
		echo "Installing pnpm (the management page is built with it)..."
		if ! sudo pacman -S --needed --noconfirm pnpm; then
			die "could not install pnpm; run: sudo pacman -S pnpm"
		fi
	fi
	command -v node >/dev/null || die "node not found; the page needs node >= 24"
	echo "Building the management page..."
	(cd "$web" && pnpm install --frozen-lockfile && pnpm build) ||
		die "pnpm build failed in ${web}"
	[[ -f "${web}/dist/index.html" ]] ||
		die "pnpm build reported success but ${web}/dist/index.html is not there"
}

validate_requirements() {
	command -v systemctl >/dev/null || die "systemctl not found; this needs systemd"
	ensure_exiftool
	ensure_ffmpeg
	build_web
	[[ -f "${REPO_ROOT}/.env" ]] ||
		die "no ${REPO_ROOT}/.env -- run scripts/register_bot.sh first"
	[[ -x "${REPO_ROOT}/run.sh" ]] || die "no executable ${REPO_ROOT}/run.sh"
	[[ -f "$TEMPLATE" ]] || die "no unit template at $TEMPLATE"
	[[ -x "${REPO_ROOT}/scripts/signal_api_watchdog.sh" ]] ||
		die "no executable ${REPO_ROOT}/scripts/signal_api_watchdog.sh"
	local unit
	for unit in "${WATCHDOG_UNITS[@]}"; do
		[[ -f "${REPO_ROOT}/scripts/${unit}" ]] || die "no unit template for ${unit}"
	done
}

# Without linger, a user unit dies at logout and never starts at boot.
require_linger() {
	if [[ "$(loginctl show-user "$USER" --property=Linger --value)" == "yes" ]]; then
		echo "== linger enabled: the bot starts at boot with nobody logged in"
		return 0
	fi
	echo "== enabling linger for $USER"
	if ! sudo -n loginctl enable-linger "$USER" 2>/dev/null; then
		echo "Error: linger is off and sudo needs a password here." >&2
		echo "       Without it the bot will NOT come back after a reboot." >&2
		echo "       Run this, then re-run with --verify-only:" >&2
		echo >&2
		echo "         sudo loginctl enable-linger $USER" >&2
		return 1
	fi
}

install_unit() {
	mkdir -p "$UNIT_DIR"
	sed "s|@REPO_ROOT@|${REPO_ROOT}|g" "$TEMPLATE" > "${UNIT_DIR}/${UNIT_NAME}"
	systemctl --user daemon-reload
	systemctl --user enable "$UNIT_NAME" >/dev/null
	systemctl --user restart "$UNIT_NAME"
	echo "== installed and started ${UNIT_DIR}/${UNIT_NAME}"
}

# The bot cannot restart the container it depends on from inside a wedged
# event loop, so recovery from a dead Signal connection lives in a timer.
install_watchdog() {
	local unit
	for unit in "${WATCHDOG_UNITS[@]}"; do
		sed "s|@REPO_ROOT@|${REPO_ROOT}|g" "${REPO_ROOT}/scripts/${unit}" >"${UNIT_DIR}/${unit}"
	done
	systemctl --user daemon-reload
	systemctl --user enable --now "$WATCHDOG_TIMER" >/dev/null
	echo "== installed and armed ${UNIT_DIR}/${WATCHDOG_TIMER}"
}

# Report what actually happened, not that the commands returned 0.
verify() {
	local port="$1"
	if ! systemctl --user is-active --quiet "$UNIT_NAME"; then
		echo "Error: ${UNIT_NAME} is not active." >&2
		systemctl --user --no-pager --lines=20 status "$UNIT_NAME" >&2 || true
		return 1
	fi
	signal_wait_for_url "http://127.0.0.1:${port}/healthz" "signal-bot" 60
	echo "== active, and answering on http://127.0.0.1:${port}/healthz"
	echo "== enabled at boot: $(systemctl --user is-enabled "$UNIT_NAME")"
	if ! systemctl --user is-active --quiet "$WATCHDOG_TIMER"; then
		echo "Error: ${WATCHDOG_TIMER} is not active; nothing will recover a dead" >&2
		echo "       connection to Signal automatically." >&2
		return 1
	fi
	systemctl --user list-timers --no-pager "$WATCHDOG_TIMER" | sed -n '2p'
}

main() {
	validate_requirements
	local port
	port="$(bot_port)"

	if [[ "$VERIFY_ONLY" != "true" ]]; then
		require_linger
		install_unit
		install_watchdog
	fi

	verify "$port"
	echo "== logs:  journalctl --user -u ${UNIT_NAME} -f"
}

while [[ $# -gt 0 ]]; do
	case $1 in
	--verify-only)
		VERIFY_ONLY="true"
		shift
		;;
	-h | --help) usage ;;
	*)
		echo "Unknown option: $1" >&2
		exit 1
		;;
	esac
done

main "$@"