#!/bin/sh
# Start Garmin Health Lab. Safe to run repeatedly: an already-running
# instance is stopped first. Intended for DSM Task Scheduler (boot-up).
APP="$(cd "$(dirname "$0")/.." && pwd)"
cd "$APP/backend" || exit 1

GUNICORN="$APP/backend/.venv/bin/gunicorn"

# Stop whatever is already running, then WAIT for the port to actually be
# free. Killing only the pid in app.pid left orphaned workers holding :8124;
# the new master then started, reported success, and served nothing — the
# site was down while every log line looked normal.
"$APP/deploy/stop.sh" >/dev/null 2>&1
i=0
while [ $i -lt 20 ]; do
  pgrep -f "$GUNICORN" >/dev/null 2>&1 || break
  sleep 1
  i=$((i + 1))
done
pkill -9 -f "$GUNICORN" 2>/dev/null
sleep 1

mkdir -p "$APP/logs"
# --timeout 300: an AI generation against the reasoning model can run for
# minutes, and gunicorn kills a worker that looks stuck before then.
nohup "$GUNICORN" \
  --workers 2 --threads 4 --timeout 300 \
  --bind 0.0.0.0:8124 \
  --access-logfile "$APP/logs/access.log" \
  --error-logfile "$APP/logs/error.log" \
  wsgi:app > "$APP/logs/stdout.log" 2>&1 &

echo $! > "$APP/app.pid"

# Confirm it is actually serving rather than just running.
i=0
while [ $i -lt 25 ]; do
  if curl -sf -m 2 -o /dev/null http://127.0.0.1:8124/api/health/status; then
    echo "started pid $(cat "$APP/app.pid") on :8124"
    exit 0
  fi
  sleep 1
  i=$((i + 1))
done

echo "FAILED to serve on :8124 — see $APP/logs/error.log" >&2
exit 1