---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference/tasks/model.yml
# DESCRIPTION: Phase 4 — HuggingFace login and Gemma 2 27B model download.
#              Idempotent: snapshot_download skips files already present.
#              Requires vault_hf_token and Gemma 2 licence accepted at
#              huggingface.co/google/gemma-2-27b-it.
# ------------------------------------------------------------------------------

- name: Write HuggingFace token to ~/.cache/huggingface/token
  ansible.builtin.copy:
    content: "{{ vault_hf_token }}"
    dest: "/home/{{ llm_venv_owner }}/.cache/huggingface/token"
    owner: "{{ llm_venv_owner }}"
    group: "{{ llm_venv_owner }}"
    mode: "0600"
  no_log: true

- name: Download Gemma 2 27B model via snapshot_download
  ansible.builtin.command:
    cmd: >
      {{ llm_venv_path }}/bin/python -c "
      from huggingface_hub import snapshot_download
      path = snapshot_download(
          '{{ llm_hf_model }}',
          cache_dir='{{ llm_hf_cache_dir }}',
      )
      print(path)
      "
    creates: "{{ llm_hf_cache_dir }}/models--{{ llm_hf_model | replace('/', '--') }}/snapshots"
  become: true
  become_user: "{{ llm_venv_owner }}"
  environment:
    HF_TOKEN: "{{ vault_hf_token }}"
    HOME: "/home/{{ llm_venv_owner }}"
  register: model_download
  timeout: 3600
  no_log: false

- name: Print model download path
  ansible.builtin.debug:
    msg: "Model available at: {{ model_download.stdout | default('already present') }}"