My-Weekly-ToDo-List/scripts/update-app.sh

#!/bin/bash
#
# Deploy script for the production host (WebApp-Testing-live).
#
# The app runs there as a PM2 process ("my-weekly-todo") from /root/My-Weekly-ToDo-List.
# It is NOT run under Docker — deploy.sh and docker-compose.yml in this repo describe an
# older Portainer setup that is not what serves todo.martin-bierschenk.de.
#
# This is the single update path. It is used both ways:
#   - by hand:   /root/My-Weekly-ToDo-List/scripts/update-app.sh [--force]
#   - at boot:   my-weekly-todo-update.service, before pm2-root.service starts the app
#
# There used to be a second, near-identical boot-update.sh. The two drifted (the npm ci fix
# from 1.114.1 only ever landed in this one), so boot-update.sh is now a shim that calls
# this script. Keep it that way: one script, one set of fixes.
#
# The whole body is wrapped in a function so bash parses it in one go: this script lives
# inside the very checkout it updates, and `git pull` rewriting it mid-run would otherwise
# make bash resume at a stale file offset.

main() {
    # pipefail matters because everything below is written through a `tee` redirect: without
    # it the shell sees tee's exit status (always 0) and a failed build looks like success.
    set -euo pipefail

    local APP_DIR="/root/My-Weekly-ToDo-List"
    local PM2_APP="my-weekly-todo"
    local LOG_FILE="/var/log/my-weekly-todo-update.log"
    local LOCK_FILE="/var/lock/my-weekly-todo-update.lock"
    local FORCE="${1:-}"

    # One redirect for the whole run: goes to the log and, when run by hand, to the console.
    exec > >(tee -a "$LOG_FILE") 2>&1

    log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1"; }

    trap 'log "!!! Update FAILED at line $LINENO (exit $?) — the running build is untouched"' ERR

    # Fail fast instead of hanging on a credential prompt when run without a terminal
    # (systemd has no tty). The host authenticates via a read-only SSH deploy key.
    export GIT_TERMINAL_PROMPT=0

    # Never let a boot run and a manual run install into the same tree at once: a half-written
    # node_modules is what leaves npm unable to clean up afterwards (ENOTEMPTY on rmdir).
    exec 9>"$LOCK_FILE"
    if ! flock -n 9; then
        log "Another update is already running — nothing to do."
        return 0
    fi

    cd "$APP_DIR"

    log "=== Update started ==="

    log "--- Ensuring main branch ---"
    git checkout main

    log "--- Fetching from git ---"
    git fetch origin main

    local LOCAL REMOTE
    LOCAL=$(git rev-parse HEAD)
    REMOTE=$(git rev-parse origin/main)

    # Rebuild when the code moved, when there is no build to serve, or when asked to.
    local NEEDS_BUILD=0
    [ "$LOCAL" != "$REMOTE" ] && NEEDS_BUILD=1
    [ ! -f "$APP_DIR/.next/standalone/server.js" ] && NEEDS_BUILD=1
    [ "$FORCE" = "--force" ] && NEEDS_BUILD=1

    if [ "$NEEDS_BUILD" -eq 0 ]; then
        log "Already up to date and a build is in place. Nothing to do."
        log "=== Update finished (no changes) ==="
        return 0
    fi

    if [ "$LOCAL" != "$REMOTE" ]; then
        log "--- Pulling latest changes ($LOCAL -> $REMOTE) ---"
        git pull origin main

        # npm ci, not npm install: it installs exactly what package-lock.json specifies and
        # never rewrites it. npm install rewrites the lockfile, which leaves the working tree
        # dirty and makes the *next* git pull abort. npm ci clears node_modules itself; if
        # that ever fails with ENOTEMPTY, remove the directory by hand and rerun.
        log "--- Installing dependencies ---"
        npm ci
    fi

    log "--- Updating database schema (safe migrate) ---"
    npx prisma migrate deploy || {
        log "migrate deploy failed, falling back to db push..."
        npx prisma db push --accept-data-loss
    }

    log "--- Regenerating Prisma client ---"
    npx prisma generate

    log "--- Building application ---"
    npm run build

    # next.config.js sets output: 'standalone', and Next.js does NOT copy public/ or
    # .next/static/ into .next/standalone — that is a documented manual step. Skipping it
    # ships new server code whose HTML references new chunk hashes while the old chunks sit
    # in the standalone tree: they 404, React never hydrates, and every page hangs on its
    # server-rendered shell ("Loading session...") while the API still answers 200.
    log "--- Copying static assets into standalone output ---"
    cp -r public .next/standalone/
    mkdir -p .next/standalone/.next/static
    cp -r .next/static .next/standalone/.next/
    cp .env .next/standalone/ 2>/dev/null || true

    # At boot this script runs before pm2-root.service, so the PM2 daemon is not up yet and
    # there is nothing to restart — pm2-root.service resurrects the app right after. Probing
    # with `pm2 describe` would be wrong here: any pm2 command spawns a daemon, and a stray
    # one started from this unit would race the real service.
    local PM2_PID_FILE="${HOME:-/root}/.pm2/pm2.pid"
    if [ -f "$PM2_PID_FILE" ] && kill -0 "$(cat "$PM2_PID_FILE")" 2>/dev/null; then
        log "--- Restarting PM2 process ---"
        pm2 restart "$PM2_APP" --update-env
        pm2 save
    else
        log "PM2 daemon is not running — leaving the start to pm2-root.service."
    fi

    log "=== Update Complete ==="
    log "Deployed version: $(node -p "require('$APP_DIR/package.json').version")"
}

main "$@"