#!/usr/bin/env bash
# ------------------------------------------------------------------------------
# FILE: vllm-workspace.sh — deployed by roles/deploy-vllm to
#       /home/{{ vllm_venv_owner }}/vllm-workspace.sh
#
# Convenience wrapper for manual debugging / smoke-testing the vLLM venv
# without having to remember the venv path or model roster each time.
# Regenerated on every Ansible run — do not hand-edit, edit the template
# instead (roles/deploy-vllm/templates/vllm-workspace.sh.j2).
# ------------------------------------------------------------------------------
set -euo pipefail

VENV="{{ vllm_venv_path }}"
CACHE="{{ vllm_hf_hub_cache }}"
API_KEY_FILE="{{ vllm_api_key_env_file }}"

usage() {
  cat <<EOF
Usage: $0 <command>

Commands:
  activate        Print the command to source the vLLM venv
  version         Print installed vLLM + torch/CUDA versions
  models          List staged model snapshots in the HF cache
  curl-models     curl /v1/models on each enabled instance (requires sudo to read API key)
  logs <unit>     Tail journalctl for a vllm systemd unit (e.g. vllm.service)
EOF
}

case "${1:-}" in
  activate)
    echo "source $VENV/bin/activate"
    ;;
  version)
    "$VENV/bin/python" -c 'import vllm, torch; print("vllm", vllm.__version__); print("torch", torch.__version__, "cuda", torch.version.cuda, "available", torch.cuda.is_available())'
    ;;
  models)
    find "$CACHE" -maxdepth 1 -type d -name 'models--*' -printf '%f\n' 2>/dev/null || echo "(no models staged yet)"
    ;;
  curl-models)
{% for item in vllm_enabled_models | default([]) %}
    echo "--- {{ item.id }} (:{{ item.port }}) ---"
    curl -s -H "Authorization: Bearer $(sudo grep -oP '(?<=VLLM_API_KEY=).*' "$API_KEY_FILE")" \
      http://127.0.0.1:{{ item.port }}/v1/models | python3 -m json.tool || true
{% endfor %}
    ;;
  logs)
    sudo journalctl -u "${2:-vllm.service}" -f
    ;;
  *)
    usage
    exit 1
    ;;
esac