drinktracker/deploy/deploy.sh

#!/usr/bin/env bash
#
# Deploy drinktracker to the production LXC.
#
# The app runs natively under systemd - no Docker. Each deploy builds into
# releases/<sha> out-of-place and swaps a symlink, so the ~3 minute build happens
# while the old release keeps serving and downtime is only the restart.
#
# Usage:  ./deploy/deploy.sh [--yes] [--no-build] [--rollback]
#
set -euo pipefail

HOST="${DT_HOST:-drinkadmin@192.168.2.169}"
SSH_KEY="${DT_SSH_KEY:-$HOME/.ssh/drinktracker_ed25519}"
APP_DIR="${DT_APP_DIR:-/opt/drinktracker}"
SVC_USER="${DT_SVC_USER:-drinktracker}"
KEEP_RELEASES=5
HEALTH_URL="http://localhost:3000/"

ASSUME_YES=0; BUILD=1; ROLLBACK=0
for arg in "$@"; do
  case "$arg" in
    --yes|-y) ASSUME_YES=1 ;;
    --no-build) BUILD=0 ;;
    --rollback) ROLLBACK=1 ;;
    *) echo "unknown option: $arg" >&2; exit 2 ;;
  esac
done

SSH=(ssh -o BatchMode=yes -o ConnectTimeout=10 -i "$SSH_KEY" "$HOST")
say() { printf '\n\033[1;36m==> %s\033[0m\n' "$*"; }
die() { printf '\n\033[1;31mFAILED: %s\033[0m\n' "$*" >&2; exit 1; }

health_poll() {
  for i in $(seq 1 30); do
    code=$("${SSH[@]}" "curl -s -o /dev/null -w '%{http_code}' -m 5 $HEALTH_URL" || echo 000)
    # 307 is the unauthenticated redirect to /login - healthy.
    case "$code" in 200|302|307) echo "  healthy (HTTP $code) after $((i*2))s"; return 0 ;; esac
    sleep 2
  done
  return 1
}

# ─── Rollback: repoint the symlink, no rebuild ───────────────────────
if [ "$ROLLBACK" -eq 1 ]; then
  say "Available releases (newest last)"
  "${SSH[@]}" "ls -1tr $APP_DIR/releases"
  CURRENT=$("${SSH[@]}" "readlink $APP_DIR/current | xargs basename")
  PREV=$("${SSH[@]}" "ls -1t $APP_DIR/releases | grep -v '^$CURRENT\$' | head -1")
  [ -n "$PREV" ] || die "no other release to roll back to"
  echo "  current=$CURRENT  ->  rolling back to $PREV"
  if [ "$ASSUME_YES" -ne 1 ]; then
    read -r -p "  proceed? [y/N] " r; [[ "$r" =~ ^[Yy]$ ]] || { echo aborted; exit 1; }
  fi
  "${SSH[@]}" "sudo -n -u $SVC_USER bash -c 'ln -sfn $APP_DIR/releases/$PREV $APP_DIR/current.new && mv -Tf $APP_DIR/current.new $APP_DIR/current'"
  "${SSH[@]}" "sudo -n systemctl restart drinktracker"
  health_poll || die "app unhealthy after rollback - journalctl -u drinktracker"
  say "Rolled back to $PREV"
  exit 0
fi

# ─── Preflight (local) ───────────────────────────────────────────────
say "Preflight"
cd "$(dirname "$0")/.."
[ -n "$(git status --porcelain)" ] && die "working tree is dirty - commit or stash first"
BRANCH=$(git rev-parse --abbrev-ref HEAD)
[ "$BRANCH" = "main" ] || die "on branch '$BRANCH', expected main"
npx tsc --noEmit || die "typecheck failed"
echo "  typecheck ok, tree clean, on main"

git -c credential.helper=store push origin main
SHA=$(git rev-parse HEAD); SHORT=${SHA:0:7}
echo "  pushed $SHORT"

# ─── Preflight (remote) ──────────────────────────────────────────────
say "Checking $HOST"
"${SSH[@]}" true || die "cannot reach $HOST with key $SSH_KEY"
for unit in postgresql@16-main minio drinktracker; do
  st=$("${SSH[@]}" "systemctl is-active $unit" || true)
  echo "  $unit: $st"
  [ "$st" = "active" ] || die "$unit is not active - fix before deploying"
done

if [ "$ASSUME_YES" -ne 1 ]; then
  CURRENT=$("${SSH[@]}" "readlink $APP_DIR/current | xargs basename")
  echo "  current release $CURRENT, deploying $SHORT"
  read -r -p "  proceed? [y/N] " r; [[ "$r" =~ ^[Yy]$ ]] || { echo aborted; exit 1; }
fi

# ─── Build (out-of-place; the running release keeps serving) ─────────
say "Syncing and building on $HOST"
"${SSH[@]}" "sudo -n -u $SVC_USER git -C $APP_DIR/repo fetch --quiet origin main && sudo -n -u $SVC_USER git -C $APP_DIR/repo reset --hard $SHA --quiet && sudo -n -u $SVC_USER git -C $APP_DIR/repo log --oneline -1"

if [ "$BUILD" -eq 1 ]; then
  # Built WITHOUT the env file, deliberately - same as the Dockerfile. next.config.mjs
  # evaluates rewrites() at build time, so sourcing the env here would bake a different
  # /minio-images destination into routes-manifest.json.
  "${SSH[@]}" "sudo -n -u $SVC_USER bash -lc '
    set -e
    cd $APP_DIR/repo
    export npm_config_cache=$APP_DIR/.npm NODE_OPTIONS=--max-old-space-size=3072
    npm ci --prefer-offline --no-audit --fund=false
    npx prisma generate
    npm run build
  '" || die "build failed"
fi

say "Assembling release $SHORT"
# Mirrors Dockerfile:24-30 - standalone bundle plus static and public copied in.
"${SSH[@]}" "sudo -n -u $SVC_USER bash -lc '
  set -e
  REL=$APP_DIR/releases/$SHORT
  rm -rf \$REL && mkdir -p \$REL/.next/cache
  cp -a $APP_DIR/repo/.next/standalone/. \$REL/
  cp -a $APP_DIR/repo/.next/static \$REL/.next/static
  cp -a $APP_DIR/repo/public \$REL/public
  du -sh \$REL
'" || die "release assembly failed"

# ─── Schema ──────────────────────────────────────────────────────────
say "Backing up database before schema push"
"${SSH[@]}" "sudo -n install -d -m 0750 /var/backups/drinktracker && sudo -n -u postgres pg_dump drinkman | gzip -9 | sudo -n tee /var/backups/drinktracker/pre-$SHORT.sql.gz >/dev/null && sudo -n ls -lh /var/backups/drinktracker/pre-$SHORT.sql.gz"

say "Applying schema"
# db push, NOT migrate deploy: production has no _prisma_migrations table, so
# migrate deploy would try to apply the init migration against populated tables.
# --accept-data-loss means removing a field from schema.prisma DROPS the column.
"${SSH[@]}" "sudo -n -u $SVC_USER bash -lc '
  set -a; . /etc/drinktracker/drinktracker.env; set +a
  cd $APP_DIR/repo && npx prisma db push --skip-generate --accept-data-loss
'" || die "prisma db push failed"

# ─── Swap and restart ────────────────────────────────────────────────
say "Swapping to $SHORT and restarting"
"${SSH[@]}" "sudo -n -u $SVC_USER bash -c 'ln -sfn $APP_DIR/releases/$SHORT $APP_DIR/current.new && mv -Tf $APP_DIR/current.new $APP_DIR/current'"
"${SSH[@]}" "sudo -n systemctl restart drinktracker"
health_poll || die "app unhealthy - check: ${SSH[*]} 'journalctl -u drinktracker -n 50'"

# ─── Verify ──────────────────────────────────────────────────────────
say "Verifying"
"${SSH[@]}" "curl -s -o /dev/null -w '  public=%{http_code}\n' -m 15 https://drinktracker.tenseconddelay.net/ || true"
"${SSH[@]}" "sudo -n journalctl -u drinktracker --since '2 min ago' | grep '\[switchboard\]' | tail -3 || echo '  (no AI calls yet)'"

say "Pruning old releases (keeping $KEEP_RELEASES)"
"${SSH[@]}" "sudo -n -u $SVC_USER bash -c 'cd $APP_DIR/releases && ls -1t | tail -n +$((KEEP_RELEASES+1)) | xargs -r rm -rf; ls -1t'"

say "Deployed $SHORT"
echo "Roll back with:  ./deploy/deploy.sh --rollback"