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

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
STACK_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"

# shellcheck disable=SC1091
source "${SCRIPT_DIR}/catalog-lib.sh"

cd "${STACK_DIR}"

PROFILE_ARG="${1:-}"

if [[ -n "${PROFILE_ARG}" ]]; then
  PROFILE_FILE="${STACK_DIR}/profiles/${PROFILE_ARG}.env"
  if [[ ! -f "${PROFILE_FILE}" ]]; then
    echo "ERROR: Profile not found: ${PROFILE_ARG}"
    echo "       Available:"
    ls -1 "${STACK_DIR}/profiles/"*.env 2>/dev/null | xargs -n1 basename | sed 's/\.env$//' | sed 's/^/         /'
    exit 1
  fi
  cp "${PROFILE_FILE}" .env
  echo "Applied profile: ${PROFILE_ARG}"
fi

if [[ ! -f .env ]]; then
  echo "ERROR: .env not found. Run: cp .env.example .env"
  echo "       Or use a profile: ./scripts/start.sh qwen3.6-27b-awq-128k"
  exit 1
fi

set -a
# shellcheck disable=SC1091
source .env
set +a

DATA_ROOT="${DATA_ROOT:-/data}"

if [[ -z "${VLLM_MODEL:-}" ]]; then
  echo "ERROR: VLLM_MODEL is empty in .env"
  echo "       Set a model, use a profile, or run:"
  echo "       ./scripts/download-model.sh qwen3.6-27b-awq-vllm"
  echo "       ./scripts/switch-model.sh qwen3.6-27b-awq-128k"
  exit 1
fi

if [[ "${VLLM_MODEL}" == *".gguf"* ]]; then
  echo "ERROR: VLLM_MODEL points to a .gguf file — standard vLLM cannot load GGUF."
  echo "       GGUF models are in models.catalog.yaml for future llama.cpp (stacks/llamacpp/)."
  echo "       For vLLM use AWQ from Hugging Face, e.g.:"
  echo "       ./scripts/download-model.sh qwen3.6-27b-awq-vllm"
  echo "       ./scripts/switch-model.sh qwen3.6-27b-awq-128k"
  exit 1
fi

if ! mountpoint -q "${DATA_ROOT}" 2>/dev/null; then
  echo "ERROR: ${DATA_ROOT} is not mounted"
  echo "       Complete disk setup (tutorial 04 part A) first"
  exit 1
fi

catalog_ensure_dirs "${DATA_ROOT}"

if ! docker info &>/dev/null; then
  echo "ERROR: Docker is not running"
  exit 1
fi

chmod +x "${SCRIPT_DIR}/vllm-entrypoint.sh" 2>/dev/null || true

echo "=== vLLM stack ==="
echo "Model:       ${VLLM_MODEL}"
echo "Served as:   ${SERVED_MODEL_NAME:-qwen3.6-27b}"
echo "Context:     ${MAX_MODEL_LEN:-131072} tokens"
echo "KV cache:    ${KV_CACHE_DTYPE:-fp8}"
echo "Quantize:    ${QUANTIZATION:-(none)}"
echo "Data root:   ${DATA_ROOT}"
echo ""

docker compose --profile vllm pull
docker compose --profile vllm up -d

echo ""
echo "Started. Follow logs:"
echo "  docker compose --profile vllm logs -f vllm"
echo ""
echo "Test when ready:"
echo "  curl -s http://localhost:${VLLM_PORT:-8000}/v1/models | jq ."