#!/usr/bin/env bash
#
# ctl.sh — Nexus dev server control script
#
# Usage:
#   ./ctl.sh start     Start the dev server (background, logs to .paperclip/dev.log)
#   ./ctl.sh stop      Gracefully stop the dev server and all child processes
#   ./ctl.sh restart   Stop then start
#   ./ctl.sh status    Show whether the server is running
#   ./ctl.sh logs      Tail the dev server log
#   ./ctl.sh fg        Start in foreground (interactive, Ctrl-C to stop)

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PIDFILE="$SCRIPT_DIR/.paperclip/dev.pid"
LOGFILE="$SCRIPT_DIR/.paperclip/dev.log"

# Read PORT from .env (default 6100) so every command uses the same port.
PORT=$(grep -s '^PORT=' "$SCRIPT_DIR/.env" | cut -d= -f2)
PORT=${PORT:-6100}

mkdir -p "$(dirname "$PIDFILE")"

is_running() {
  [[ -f "$PIDFILE" ]] || return 1
  local pid
  pid=$(<"$PIDFILE")
  kill -0 "$pid" 2>/dev/null
}

get_pid() {
  [[ -f "$PIDFILE" ]] && cat "$PIDFILE" || echo ""
}

do_start() {
  if is_running; then
    echo "Already running (pid $(get_pid)). Use '$0 restart' to restart."
    exit 0
  fi

  echo "Starting Nexus dev server..."
  cd "$SCRIPT_DIR"
  # setsid creates a new process group so 'kill -- -PGID' reaches all children
  setsid pnpm dev >> "$LOGFILE" 2>&1 &
  local parent_pid=$!
  echo "$parent_pid" > "$PIDFILE"

  # Wait for health endpoint
  local ready=false
  for i in $(seq 1 30); do
    if curl -sf "http://localhost:$PORT/api/health" > /dev/null 2>&1; then
      ready=true
      break
    fi
    sleep 1
  done

  if $ready; then
    echo "Server ready (pid $parent_pid) — http://localhost:$PORT"
    echo "Logs: $LOGFILE"
  else
    echo "Server started (pid $parent_pid) but health check not yet responding."
    echo "Check logs: tail -f $LOGFILE"
  fi
}

do_stop() {
  if ! is_running; then
    echo "Not running."
    # Clean up orphans anyway
    "$SCRIPT_DIR/scripts/kill-dev.sh" 2>/dev/null || true
    rm -f "$PIDFILE"
    return 0
  fi

  local pid
  pid=$(get_pid)
  echo "Stopping Nexus dev server (pid $pid)..."

  # Kill the entire process group (negative PID = PGID).
  # setsid in do_start makes the parent the session/group leader,
  # so this reaches all children: pnpm, tsx, cross-env, node server, etc.
  kill -TERM -- -"$pid" 2>/dev/null || kill -TERM "$pid" 2>/dev/null || true

  # Wait up to 5s for graceful shutdown
  local waited=0
  while kill -0 "$pid" 2>/dev/null && (( waited < 50 )); do
    sleep 0.1
    ((waited += 1))
  done

  # Force-kill any stragglers in the group
  if kill -0 "$pid" 2>/dev/null; then
    echo "Sending SIGKILL to remaining processes..."
    kill -KILL -- -"$pid" 2>/dev/null || true
  fi

  # Use kill-dev.sh to mop up embedded postgres
  "$SCRIPT_DIR/scripts/kill-dev.sh" 2>/dev/null || true

  rm -f "$PIDFILE"
  echo "Stopped."
}

do_status() {
  if ! is_running; then
    rm -f "$PIDFILE"
    echo "Nexus is not running."
    return
  fi

  local pid
  pid=$(get_pid)

  # Uptime from pidfile modification time (written at start)
  local uptime started_at
  if [[ -f "$PIDFILE" ]]; then
    local now pidfile_epoch
    now=$(date +%s)
    pidfile_epoch=$(stat -c %Y "$PIDFILE" 2>/dev/null || echo "$now")
    local diff=$(( now - pidfile_epoch ))
    local days=$(( diff / 86400 ))
    local hours=$(( (diff % 86400) / 3600 ))
    local mins=$(( (diff % 3600) / 60 ))
    if (( days > 0 )); then
      uptime="${days}d ${hours}h ${mins}m"
    elif (( hours > 0 )); then
      uptime="${hours}h ${mins}m"
    else
      uptime="${mins}m"
    fi
    started_at=$(date -d "@$pidfile_epoch" "+%Y-%m-%d %H:%M" 2>/dev/null || echo "?")
  else
    uptime="?"
    started_at="?"
  fi

  # Query health endpoint for deploy info
  local health
  health=$(curl -sf --max-time 2 "http://localhost:$PORT/api/health" 2>/dev/null || echo "")

  local mode exposure version
  mode=$(echo "$health" | grep -oP '"deploymentMode"\s*:\s*"\K[^"]+' || echo "?")
  exposure=$(echo "$health" | grep -oP '"deploymentExposure"\s*:\s*"\K[^"]+' || echo "?")
  version=$(echo "$health" | grep -oP '"version"\s*:\s*"\K[^"]+' || echo "?")

  # Detect listen host/port from .env or defaults
  local host port
  host=$(grep -s '^HOST=' "$SCRIPT_DIR/.env" | cut -d= -f2 || echo "127.0.0.1")
  host=${host:-127.0.0.1}
  port=$PORT

  # LAN IP (first non-loopback IPv4)
  local lan_ip
  lan_ip=$(ip -4 -o addr show scope global 2>/dev/null | awk '{print $4}' | cut -d/ -f1 | head -1 || echo "")

  # Detect embedded postgres
  local pg_pid pg_port pg_status
  pg_pid=$(ps --ppid "$pid" -o pid,args --no-headers -w 2>/dev/null | grep postgres | awk '{print $1}' | head -1 || echo "")
  if [[ -z "$pg_pid" ]]; then
    # postgres may be deeper in the tree — search all descendants
    pg_pid=$(ps -eo pid,args --no-headers 2>/dev/null | grep "[p]ostgres -D" | awk '{print $1}' | head -1 || echo "")
  fi
  pg_port=$(grep -s 'embeddedPostgresPort' "$HOME/.paperclip/instances/default/config.json" 2>/dev/null | grep -oP '\d+' || echo "54329")
  if [[ -n "$pg_pid" ]]; then
    pg_status="running (pid $pg_pid, port $pg_port)"
  else
    pg_status="not detected"
  fi

  # Vite HMR port
  local hmr_port=$(( port + 10000 ))

  # Process count in group
  local proc_count
  proc_count=$(ps -g "$pid" --no-headers 2>/dev/null | wc -l || echo "?")

  # Print status
  echo ""
  echo "  Nexus Dev Server"
  echo "  ──────────────────────────────────────────"
  echo "  Status        running since $started_at ($uptime)"
  echo "  Version       $version"
  echo "  PID           $pid ($proc_count processes)"
  echo "  Mode          $mode ($exposure)"
  echo ""
  echo "  API           http://localhost:$port/api"
  echo "  UI            http://localhost:$port"
  if [[ "$host" == "0.0.0.0" && -n "$lan_ip" ]]; then
  echo "  LAN           http://$lan_ip:$port"
  fi
  echo "  HMR           ws://localhost:$hmr_port"
  echo ""
  echo "  Postgres      $pg_status"
  echo "  Log           $LOGFILE"
  echo ""
}

do_logs() {
  if [[ -f "$LOGFILE" ]]; then
    tail -f "$LOGFILE"
  else
    echo "No log file at $LOGFILE"
  fi
}

do_fg() {
  if is_running; then
    echo "Already running in background (pid $(get_pid)). Stop it first with '$0 stop'."
    exit 1
  fi
  cd "$SCRIPT_DIR"
  exec pnpm dev
}

case "${1:-}" in
  start)   do_start ;;
  stop)    do_stop ;;
  restart) do_stop; do_start ;;
  status)  do_status ;;
  logs)    do_logs ;;
  fg)      do_fg ;;
  *)
    echo "Usage: $0 {start|stop|restart|status|logs|fg}"
    exit 1
    ;;
esac