#!/usr/bin/env bash
# ci-cd.yml › Build & Deploy › Verify backend — wait until erpcore.service answers /health, and fail the job otherwise.
#
# EF migrations + seeding run BEFORE the app starts listening, so a slow start is normal. Only a
# crash (unit failed, or systemd auto-restarted it) or the ceiling counts as failure — a crashed
# service fails within seconds, and a slow but live migration is never cut short by a tight timer.
#
# Env: SERVICE (erpcore.service) · BACKEND_PORT (5220) · HEALTH_TIMEOUT seconds (300)
#      RESTARTS_AT_START — NRestarts captured right after `systemctl start` (the Start step exports it)
set -euo pipefail

service="${SERVICE:-erpcore.service}"
port="${BACKEND_PORT:-5220}"
timeout="${HEALTH_TIMEOUT:-300}"
restarts_at_start="${RESTARTS_AT_START:-$(systemctl show -p NRestarts --value "$service")}"

show_journal() { journalctl -u "$service" -n 80 --no-pager || true; }

deadline=$((SECONDS + timeout))
while ((SECONDS < deadline)); do
  if curl -fsS --max-time 5 -o /dev/null "http://127.0.0.1:$port/health" 2>/dev/null; then
    echo "✅ $service is healthy (after ${SECONDS}s)"
    exit 0
  fi
  state="$(systemctl show -p ActiveState --value "$service")"
  restarts="$(systemctl show -p NRestarts --value "$service")"
  if [[ "$state" == failed || "$restarts" != "$restarts_at_start" ]]; then
    echo "❌ $service crashed during startup (state=$state, restarts $restarts_at_start → $restarts)" >&2
    show_journal
    exit 1
  fi
  sleep 3
done

echo "❌ $service did not answer /health within ${timeout}s (still starting? DB reachable?)" >&2
show_journal
exit 1