run.sh

#!/usr/bin/env bash
set -euo pipefail

# Default to 1 worker to prevent OOM on low-memory hosts
WORKERS_VALUE="${WORKERS:-1}"
TIMEOUT_VALUE="${TIMEOUT:-120}"
PORT_VALUE="${PORT:-10000}"

# Initialize the database
echo "Initializing database..."
python scripts/init_pgvector.py

echo "Starting gunicorn on port ${PORT_VALUE} with ${WORKERS_VALUE} workers and timeout ${TIMEOUT_VALUE}s"
export PYTHONPATH="/app${PYTHONPATH:+:$PYTHONPATH}"

# Start gunicorn in background so we can trap signals and collect diagnostics
gunicorn \
  --bind 0.0.0.0:${PORT_VALUE} \
  --workers "${WORKERS_VALUE}" \
  --timeout "${TIMEOUT_VALUE}" \
  --log-level debug \
  --access-logfile - \
  --error-logfile - \
  --capture-output \
  --config gunicorn.conf.py \
  app:app &

GUNICORN_PID=$!

# Trap TERM and INT, log diagnostics, forward the signal to gunicorn, and wait
handle_term() {
  echo "===== SIGTERM received at $(date -u +'%Y-%m-%dT%H:%M:%SZ') ====="
  echo "--- Top processes by RSS ---"
  ps aux --sort=-rss | head -n 20 || true
  echo "--- /proc/meminfo (if available) ---"
  cat /proc/meminfo || true
  echo "Forwarding SIGTERM to gunicorn (pid ${GUNICORN_PID})"
  kill -TERM "${GUNICORN_PID}" 2>/dev/null || true
  # Wait for gunicorn to exit
  wait "${GUNICORN_PID}" || true
  echo "Gunicorn exited; wrapper exiting"
  exit 0
}
trap 'handle_term' SIGTERM SIGINT

# Give gunicorn a moment to start before pre-warm
echo "Waiting for server to start to pre-warm..."
sleep 5

# Pre-warm application (best-effort; don't fail startup if warm request fails)
echo "Pre-warming application..."
curl -sS -X POST http://localhost:${PORT_VALUE}/chat \
  -H "Content-Type: application/json" \
  -d '{"message":"pre-warm"}' \
  --max-time 180 --fail >/dev/null 2>&1 || echo "Pre-warm request failed but continuing..."

echo "Server is running."

# Wait for gunicorn to exit and forward its exit code
wait "${GUNICORN_PID}"
EXIT_CODE=$?
echo "Gunicorn stopped with exit code ${EXIT_CODE}"
exit "${EXIT_CODE}"