EpicNext-Cms/scripts/ci-deploy.sh

#!/usr/bin/env bash
# One lock covers build, migrations, cutover, health checks and smoke tests.
set -Eeuo pipefail

deploy_dir="${CMS_DEPLOY_DIR:-/var/www/atom-nexst}"
branch="${DEPLOY_BRANCH:-main}"
case "$branch" in main|master) ;; *) echo "Unsupported deployment branch" >&2; exit 1 ;; esac
exec 9>"$deploy_dir/.deploy.lock"
flock -w 1800 9

sha="$(git rev-parse HEAD)"
[[ "$sha" =~ ^[0-9a-f]{40}$ ]] || { echo "Invalid commit" >&2; exit 1; }
image="epicnext-cms:$sha"
previous_name=""
previous_image=""
secondary_name=""
secondary_backup="epicnext-cms-rollback-secondary"
secondary_backup_created=0
backup_name="epicnext-cms-rollback"
cutover_started=0
candidate_attempted=0
backup_created=0

# ── Blue/green ──
# De app draait met `--net=host`, dus elke replica neemt een eigen host-poort in
# plaats van een gedeelde docker-poort. Daardoor zijn er twee vaste slots en kan
# een release naast de live release opstarten. De nginx-upstream wijst pas naar
# de nieuwe release nadat die gezond is én de browsersmoke-test heeft gewonnen.
slot_a_port=3002
slot_b_port=3003
slot_a_container="epicnext-cms-app"
slot_b_container="epicnext-cms-green"
# Overridable zodat de simulatietests een pad kunnen opgeven dat niet bestaat en
# zo het in-place pad kunnen testen, en zodat een host met een andere
# nginx-indeling niet stilvalt op een release.
upstream_file="${CMS_UPSTREAM_FILE:-/etc/nginx/snippets/cms_upstream_servers.conf}"
nginx_site="${CMS_NGINX_SITE:-/etc/nginx/sites-enabled/cms.conf}"
active_port=""
old_port=""
new_port=""
old_container=""
new_container=""
blue_green=0

# Resource limits voor de container. Zonder deze limieten kan één geheugenlek de
# hele host vullen, met MariaDB, nginx en Traefik als slachtoffer. 2 CPU laat
# achtergrondwerk toe zonder de hele kernel aan één release te geven.
mem_limit="4g"
mem_swap_limit="5g"
cpu_limit="2"
pids_limit="512"

is_current() {
  local head
  head="$(git ls-remote --exit-code origin "refs/heads/$branch")" || return 2
  head="${head%%[[:space:]]*}"
  if [ "$head" != "$sha" ]; then
    echo "Skipping superseded commit $sha (branch now at $head)"
    return 1
  fi
}

check_current() {
  local status=0
  is_current || status=$?
  case "$status" in 0) ;; 1) exit 0 ;; *) echo "Cannot verify remote branch" >&2; exit 1 ;; esac
}

healthy() {
  local port="${1:-$slot_a_port}"
  local attempt
  for attempt in $(seq 1 30); do
    if curl -sf --max-time 5 "http://127.0.0.1:$port/api/health" | grep -q '"database":true'; then return 0; fi
    sleep 3
  done
  return 1
}

# Staat er een blue/green-upstream? Zonder die bestanden blijft dit script op de
# oude, in-place cutover vallen, zodat een host met een andere nginx-indeling
# niet stilvalt op een upgrade.
detect_blue_green() {
  [ -r "$upstream_file" ] || return 1
  grep -qs 'cms_app' "$nginx_site" || return 1
  return 0
}

# Welke poort is op dit moment ÉCHT live? Kijk niet naar het upstream-bestand
# (dat kan door een losse `docker compose up` zijn ingehaald en naar een dood
# slot wijzen), maar test welk slot werkelijk antwoordt op /api/health. Alleen
# in een dubbelzinnige situatie (geen óf beide slots gezond) valt het script
# terug op de huidige nginx-pointer; onbekend = slot A (eerste release op 3002).
read_active_port() {
  local live="" port="" result=""
  local count=0
  for port in "$slot_a_port" "$slot_b_port"; do
    if curl -sf --max-time 3 "http://127.0.0.1:$port/api/health" | grep -q '"database":true'; then
      live="$live $port"
    fi
  done
  for port in $live; do count=$((count + 1)); result="$port"; done
  if [ "$count" -eq 1 ]; then
    printf '%s' "$result"
    return 0
  fi
  port="$(grep -oE '127\.0\.0\.1:[0-9]+' "$upstream_file" 2>/dev/null | head -1 | cut -d: -f2 || true)"
  case "$port" in
    "$slot_b_port") printf '%s' "$slot_b_port" ;;
    *) printf '%s' "$slot_a_port" ;;
  esac
}

# Zet de nginx-upstream op de nieuwe poort en herlaadt graceful.
#
# De nieuwe inhoud wordt eerst echt weggeschreven en dán getest: `nginx -t` leest
# het include-bestand van schijf, dus alleen achteraf testen zou de oude, werkende
# configuratie blijven valideren. Faalt de test, dan gaat het origineel onmiddellijk
# terug en raakt de live release niets.
switch_upstream() {
  local port="$1"
  local backup="${upstream_file}.deploy.bak"
  if ! cp "$upstream_file" "$backup" 2>/dev/null; then
    echo "Cannot back up $upstream_file; refusing to cut over" >&2
    return 1
  fi
  {
    echo "# Geschreven door scripts/ci-deploy.sh op $(date -u +%FT%TZ) voor release $sha."
    echo "# Niet met de hand bewerken: de volgende deploy overschrijft dit bestand."
    echo "server 127.0.0.1:${port} max_fails=2 fail_timeout=10s;"
  } >"$upstream_file"
  if ! nginx -t >/dev/null 2>&1; then
    echo "nginx rejected the new upstream; restoring the previous one" >&2
    mv "$backup" "$upstream_file"
    return 1
  fi
  if ! nginx -s reload; then
    echo "nginx reload failed; restoring the previous upstream" >&2
    mv "$backup" "$upstream_file"
    nginx -s reload || true
    return 1
  fi
  rm -f "$backup"
  # Even de tijd voor de graceful reload om de nieuwe worker te laten starten.
  sleep 1
  return 0
}

# Start de kandidaat op een eigen host-poort.
#
# De resource limits staan hier bewust bij de `docker run` en niet alleen in
# docker-compose.yml: een release wordt hier gestart en gebruikt compose helemaal
# niet, dus limieten die alleen in de compose stonden zouden in productie nooit
# gelden.
start_candidate() {
  local port="$1" name="$2"
  (
    set -a
    # shellcheck disable=SC1091
    . "$deploy_dir/.env"
    set +a
    ENV_ARGS=()
    while IFS='=' read -r key _; do
      case "$key" in ''|'#'*|*[!A-Za-z0-9_]* ) continue ;; esac
      ENV_ARGS+=(-e "$key")
    done < "$deploy_dir/.env"
    docker run -d --name "$name" --restart always --net=host \
      --memory="$mem_limit" --memory-swap="$mem_swap_limit" \
      --cpus="$cpu_limit" --pids-limit="$pids_limit" \
      "${ENV_ARGS[@]}" -e "PORT=$port" -e HOSTNAME=0.0.0.0 \
      -v "$deploy_dir/public/nitro-assets:/app/public/nitro-assets" \
      -v "$deploy_dir/public/swf:/app/public/swf" \
      -v "$deploy_dir/storage:/app/storage" \
      -v /var/www/Gamedata:/var/www/Gamedata \
      "$image"
  )
}

finish() {
  local status=$?
  trap - EXIT
  if [ "$status" -ne 0 ] && [ "$blue_green" -eq 1 ]; then
    # Er zijn twee soorten falen, en het verschil bepaalt hoeveel werk terug moet.
    if [ "$cutover_started" -eq 0 ]; then
      # De live release draait nog ongestoord; alleen de kandidaat opruimen.
      echo "Deployment failed before cutover; the live release was never stopped" >&2
      if [ "$candidate_attempted" -eq 1 ] && [ -n "$new_container" ]; then
        docker logs "$new_container" --tail 50 >&2 || true
        docker rm -f "$new_container" || true
      fi
    else
      # nginx wijst nu naar de kandidaat. Eerst het verkeer terug, dan pas de
      # kandidaat weghalen, anders zou de site 502-en terwijl we terugdraaien.
      echo "Deployment failed after cutover; rolling back to port $old_port" >&2
      if [ -n "$new_container" ]; then docker logs "$new_container" --tail 50 >&2 || true; fi
      if [ -n "$old_port" ]; then switch_upstream "$old_port" || true; fi
      if [ -n "$new_container" ]; then docker rm -f "$new_container" || true; fi
      if [ -n "$old_container" ] && docker start "$old_container" >/dev/null 2>&1; then
        if healthy "$old_port"; then
          echo "Rollback verified on port $old_port"
        else
          echo "ERROR: previous container did not return to a healthy state" >&2
        fi
      else
        echo "ERROR: no previous container to roll back to" >&2
      fi
    fi
  elif [ "$status" -ne 0 ] && [ "$cutover_started" -eq 1 ]; then
    # In-place pad (geen blue/green-upstream): het oude scriptgedrag.
    echo "Deployment failed; restoring previous container" >&2
    docker logs epicnext-cms-app --tail 50 >&2 || true
    if command -v ss >/dev/null 2>&1; then ss -ltnp 'sport = :3002' >&2 || true; fi
    if [ "$candidate_attempted" -eq 1 ]; then docker rm -f epicnext-cms-app || true; fi
    if [ "$backup_created" -eq 1 ]; then docker rename "$backup_name" "$previous_name" || true; fi
    if [ "$secondary_backup_created" -eq 1 ]; then
      docker rename "$secondary_backup" "$secondary_name" || true
    fi
    if [ -n "$previous_name" ]; then
      if docker start "$previous_name" && healthy; then
        echo "Rollback verified: $previous_image"
      else
        echo "ERROR: previous container could not be restored to healthy state" >&2
      fi
    else
      echo "No previous container exists; rollback is unavailable" >&2
    fi
    if [ "$secondary_backup_created" -eq 1 ]; then docker start "$secondary_name" || true; fi
  fi
  exit "$status"
}
trap finish EXIT
trap 'exit 130' INT
trap 'exit 143' TERM

check_current
# Read-only ownership evidence before any build or container cutover.
if command -v ss >/dev/null 2>&1; then
  listeners="$(ss -ltnp 'sport = :3002' 2>/dev/null || true)"
  printf '%s\n' "$listeners"
  while read -r listener_pid; do
    [ -n "$listener_pid" ] || continue
    printf 'Port owner PID=%s cwd=' "$listener_pid"
    readlink "/proc/$listener_pid/cwd" || true
    cat "/proc/$listener_pid/cgroup" 2>/dev/null || true
    ps -o pid=,ppid=,user=,comm= -p "$listener_pid" || true
  done < <(printf '%s' "$listeners" | grep -o 'pid=[0-9]*' | cut -d= -f2 | sort -u)
fi
for managed_name in epicnext-cms epicnext-cms-app; do
  docker inspect --format '{{.Name}} running={{.State.Running}} pid={{.State.Pid}} image={{.Image}}' "$managed_name" 2>/dev/null || true
done
[ "$deploy_dir/.env" -ef .env ] || cp "$deploy_dir/.env" .env

# De migraties draaien op de host tegen DATABASE_URL, niet in de container. Die
# waarde staat alleen in $deploy_dir/.env, dus controleer hem hier: anders
# bouwen we eerst een image en doorlopen we de browsergate voordat `db:migrate`
# op een lege DATABASE_URL stukloopt. Dat is een halve release voor niets.
if ! grep -qs '^DATABASE_URL=' .env; then
  echo "Error: DATABASE_URL ontbreekt in $deploy_dir/.env" >&2
  echo "       Zet daar een DATABASE_URL (mysql://user:pass@host:3306/db) en draai opnieuw." >&2
  echo "       De live release is niet aangeraakt; deze release is niet uitgerold." >&2
  exit 1
fi

pnpm install --frozen-lockfile
pnpm exec playwright install chromium

echo "Building $image"
DOCKER_BUILDKIT=1 docker build --network=host --progress=plain --cache-from epicnext-cms:latest \
  --build-arg NEXT_DEPLOYMENT_ID="$sha" -t "$image" .
check_current
# Read reports from the already-built image; do not start an extra application.
report_container=""
if report_container="$(docker create --entrypoint /bin/true "$image")" && [ -n "$report_container" ]; then
  mkdir -p build-reports
  if docker cp "$report_container:/app/build-reports/." build-reports && [ -s build-reports/report.md ]; then
    cat build-reports/report.md
    if [ -n "${GITHUB_STEP_SUMMARY:-}" ]; then
      cat build-reports/report.md >> "$GITHUB_STEP_SUMMARY" || echo "Warning: could not append performance summary" >&2
    fi
  else
    echo "Warning: build performance report unavailable" >&2
  fi
  docker rm "$report_container" >/dev/null
else
  echo "Warning: could not extract build performance report" >&2
fi
# Exercise the candidate with disposable services before any live migration or cutover.
NEWS_E2E_IMAGE="$image" NEWS_E2E_RELEASE="$sha" node --import tsx e2e/news-real/run.ts
check_current
pnpm db:migrate
check_current

# ── Blue/green: bepaal wie live is en waar de kandidaat mag starten ──
if detect_blue_green; then
  blue_green=1
  active_port="$(read_active_port)"
  if [ "$active_port" = "$slot_b_port" ]; then
    old_port=$slot_b_port; new_port=$slot_a_port
    old_container=$slot_b_container; new_container=$slot_a_container
  else
    old_port=$slot_a_port; new_port=$slot_b_port
    old_container=$slot_a_container; new_container=$slot_b_container
  fi
  echo "Live release keeps serving port $old_port; candidate starts on port $new_port"
  # Rollback-evidence vastleggen voordat er iets wordt veranderd.
  if docker inspect "$old_container" >/dev/null 2>&1; then
    previous_name="$old_container"
    previous_image="$(docker inspect --format '{{.Image}}' "$old_container")"
    docker tag "$previous_image" epicnext-cms:previous
  else
    # Eerste release op een verse blue/green-opstelling: er is nog niets live.
    previous_name=""
    old_container=""
  fi
else
  blue_green=0
  # Prefer the active CI container, or the active legacy compose container.
  for name in epicnext-cms epicnext-cms-app; do
    if [ "$(docker inspect --format '{{.State.Running}}' "$name" 2>/dev/null || true)" = true ]; then
      if [ -z "$previous_name" ]; then previous_name="$name"; else secondary_name="$name"; fi
    fi
  done
  if [ -z "$previous_name" ]; then
    for name in epicnext-cms-app epicnext-cms; do
      if docker inspect "$name" >/dev/null 2>&1; then previous_name="$name"; break; fi
    done
  fi
  if [ -n "$previous_name" ]; then
    previous_image="$(docker inspect --format '{{.Image}}' "$previous_name")"
    docker tag "$previous_image" epicnext-cms:previous
  fi
  # Remove a stopped leftover CI container when the compose container is active.
  if [ "$previous_name" != epicnext-cms-app ] && [ "$secondary_name" != epicnext-cms-app ] && docker inspect epicnext-cms-app >/dev/null 2>&1; then
    docker rm epicnext-cms-app
  fi
fi
if docker inspect "$backup_name" >/dev/null 2>&1; then
  echo "Unresolved rollback container exists; refusing to overwrite it" >&2
  exit 1
fi

# The avatar/badge disk cache lives on the host bind and is written by uid 33
# inside the container. Root-owned directories make every cache write fail
# silently, which turns each avatar into a fresh live render.
for cache_dir in avatars badges; do
  if ! install -d -o 33 -g 33 -m 0750 "$deploy_dir/storage/imaging/$cache_dir" 2>/dev/null; then
    mkdir -p "$deploy_dir/storage/imaging/$cache_dir" 2>/dev/null || true
  fi
done
chown -R 33:33 "$deploy_dir/storage/imaging" 2>/dev/null || true

if [ "$blue_green" -eq 1 ]; then
  # 1. Maak de doel-poort vrij. Alles wat daar draait is per definitie niet live,
  #    want nginx wijst nog naar old_port. Een restje van een mislukte eerdere
  #    deploy mag de nieuwe release niet blokkeren.
  if docker inspect "$new_container" >/dev/null 2>&1; then
    docker rm -f "$new_container"
  fi

  # 2. Start de kandidaat ernaast. De live release draait ononderbroken door.
  candidate_attempted=1
  start_candidate "$new_port" "$new_container"

  # 3. Gezond? Release-hash klopt? Browsersmoke-test? Pas dan hoeft het oude
  #    release het veld te ruimen — anders zou een mislukte e2e-test pas ná de
  #    cutover de productie breken in plaats van ervoor.
  healthy "$new_port"
  node scripts/verify-deployed-release.mjs "http://127.0.0.1:$new_port/api/health" "$sha"
  PLAYWRIGHT_BASE_URL="http://127.0.0.1:$new_port" pnpm test:e2e

  # 4. Het enige onomkeerbare moment: vanaf hier wijst nginx naar de kandidaat.
  cutover_started=1
  switch_upstream "$new_port"
  echo "Cut over to port $new_port; retiring port $old_port"

  # 5. Nu mag de oude release weg. Pas ná de swap, zodat er nooit een moment is
  #    waarop er geen enkele container draait.
  if [ -n "$old_container" ] && docker inspect "$old_container" >/dev/null 2>&1; then
    docker stop "$old_container"
    docker rename "$old_container" "$backup_name"
    backup_created=1
  fi
  verified_image="$(docker inspect --format '{{.Image}}' "$new_container")"
else
  # In-place pad, alleen voor hosts zonder blue/green-upstream.
  cutover_started=1
  # Both legacy Compose and CI containers can exist after earlier failed updates.
  # Preserve each before releasing the shared host port; never kill an arbitrary PID.
  if [ -n "$secondary_name" ]; then
    docker stop "$secondary_name"
    docker rename "$secondary_name" "$secondary_backup"
    secondary_backup_created=1
  fi
  if [ -n "$previous_name" ]; then
    docker stop "$previous_name"
    docker rename "$previous_name" "$backup_name"
    backup_created=1
  fi
  candidate_attempted=1
  start_candidate 3002 epicnext-cms-app
  healthy 3002
  node scripts/verify-deployed-release.mjs http://127.0.0.1:3002/api/health "$sha"
  PLAYWRIGHT_BASE_URL=http://127.0.0.1:3002 pnpm test:e2e
  verified_image="$(docker inspect --format '{{.Image}}' epicnext-cms-app)"
fi
docker tag "$verified_image" "epicnext-cms:verified-$sha"
docker tag "$verified_image" epicnext-cms:latest
cutover_started=0
if [ "$backup_created" -eq 1 ]; then docker rm "$backup_name" || true; fi
if [ "$secondary_backup_created" -eq 1 ]; then docker rm "$secondary_backup" || true; fi


echo "Deployment verified: $sha"
# Een deploy kan de game client, furnidata (gamedata), camera en public API data
# verversen. Laat de Cloudflare edge-cache van die tags los (best-effort: alleen
# wanneer er een echte token + zone-id geconfigureerd is; no-op anders).
if [ -x "$deploy_dir/scripts/cf-purge.sh" ]; then
  bash "$deploy_dir/scripts/cf-purge.sh" cms-public cms-gamedata cms-client cms-camera || true
fi
# Retain the current and previous releases; do not remove arbitrary named tags.
while IFS= read -r tag; do
  if [[ "$tag" =~ ^epicnext-cms:(verified-)?[0-9a-f]{40}$ ]] && [ "$tag" != "$image" ] && [ "$tag" != "epicnext-cms:verified-$sha" ]; then
    tagged_image="$(docker image inspect --format '{{.Id}}' "$tag" 2>/dev/null || true)"
    if [ -n "$tagged_image" ] && [ "$tagged_image" != "$previous_image" ]; then docker image rm "$tag" || true; fi
  fi
done < <(docker image ls --format '{{.Repository}}:{{.Tag}}' epicnext-cms)
# Reclaim build cache, unreferenced images and long-stopped containers. Never
# volumes; retention boundaries are enforced inside docker-prune.sh.
bash "$deploy_dir/scripts/docker-prune.sh" || true