#!/bin/bash
  #

  # Start reranker service from isolated venv (.venv-reranker).

  #

  set -euo pipefail

  PROJECT_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
  cd "${PROJECT_ROOT}"

  RERANKER_VENV="${RERANKER_VENV:-${PROJECT_ROOT}/.venv-reranker}"
  PYTHON_BIN="${RERANKER_VENV}/bin/python"
  
  if [[ ! -x "${PYTHON_BIN}" ]]; then
    echo "ERROR: reranker venv not found: ${RERANKER_VENV}" >&2
    echo "Please run: ./scripts/setup_reranker_venv.sh" >&2
    exit 1
  fi
  

  # Load .env without activating main venv.
  # shellcheck source=scripts/lib/load_env.sh
  source "${PROJECT_ROOT}/scripts/lib/load_env.sh"
  load_env_file "${PROJECT_ROOT}/.env"

  
  RERANKER_HOST="${RERANKER_HOST:-0.0.0.0}"
  RERANKER_PORT="${RERANKER_PORT:-6007}"

  RERANK_BACKEND=$("${PYTHON_BIN}" -c "from config.services_config import get_rerank_backend_config; print(get_rerank_backend_config()[0])")
  
  # Keep vLLM/triton/torch caches out of system disk.
  RERANKER_RUNTIME_DIR="${RERANKER_RUNTIME_DIR:-${PROJECT_ROOT}/.runtime/reranker}"
  mkdir -p "${RERANKER_RUNTIME_DIR}/home" \
           "${RERANKER_RUNTIME_DIR}/cache" \
           "${RERANKER_RUNTIME_DIR}/config" \
           "${RERANKER_RUNTIME_DIR}/triton" \
           "${RERANKER_RUNTIME_DIR}/torch_compile" \
           "${RERANKER_RUNTIME_DIR}/tmp"
  export HOME="${RERANKER_RUNTIME_DIR}/home"
  export XDG_CACHE_HOME="${RERANKER_RUNTIME_DIR}/cache"
  export XDG_CONFIG_HOME="${RERANKER_RUNTIME_DIR}/config"
  export TRITON_CACHE_DIR="${RERANKER_RUNTIME_DIR}/triton"
  export TORCHINDUCTOR_CACHE_DIR="${RERANKER_RUNTIME_DIR}/torch_compile"
  export TMPDIR="${RERANKER_RUNTIME_DIR}/tmp"
  export VLLM_NO_USAGE_STATS="${VLLM_NO_USAGE_STATS:-1}"
  export PATH="${RERANKER_VENV}/bin:${PATH}"
  
  if [[ "${RERANK_BACKEND}" == "qwen3_vllm" ]]; then
    if ! command -v nvidia-smi >/dev/null 2>&1 || ! nvidia-smi >/dev/null 2>&1; then
      echo "ERROR: qwen3_vllm backend requires NVIDIA GPU, but nvidia-smi is unavailable." >&2
      exit 1
    fi
    if ! "${PYTHON_BIN}" - <<'PY'
  try:
      import vllm  # noqa: F401
      import torch
      if not torch.cuda.is_available():
          raise SystemExit(1)
  except Exception:
      raise SystemExit(1)
  PY
    then
      echo "ERROR: qwen3_vllm backend requires vllm + CUDA runtime in ${RERANKER_VENV}." >&2
      echo "Please run: ./scripts/setup_reranker_venv.sh and verify CUDA is available." >&2
      exit 1
    fi
  fi

  
  echo "========================================"
  echo "Starting Reranker Service"
  echo "========================================"

  echo "Python: ${PYTHON_BIN}"

  echo "Host: ${RERANKER_HOST}"
  echo "Port: ${RERANKER_PORT}"

  echo "Backend: ${RERANK_BACKEND}"
  echo "Runtime dir: ${RERANKER_RUNTIME_DIR}"

  echo
  

  exec "${PYTHON_BIN}" -m uvicorn reranker.server:app \

    --host "${RERANKER_HOST}" \
    --port "${RERANKER_PORT}" \
    --workers 1