# ------------------------------------------------------------------------------
# FILE: roles/deploy-vllm/tasks/models.yml
# PHASE 2: Model downloads via huggingface-cli into {{ vllm_hf_hub_cache }}.
#
# Idempotency: HuggingFace's on-disk cache layout is
#   {cache}/models--{org}--{repo}/snapshots/{revision}/...
# We stat for an existing snapshots dir before downloading — if present with
# at least one entry, skip (huggingface-cli download is itself resumable/
# idempotent, but this avoids even the "check remote manifest" round trip on
# every run and gives a clean "already staged" line in output).
#
# Pitfall (t_3dddf37d, homelab-llm-inference skill): a config/template landing
# is NOT the same as the model being staged. Always verify via `ls`/`du` on
# the actual host, never trust a prior task's claim alone.
# ------------------------------------------------------------------------------

- name: Ensure model cache directory exists
  ansible.builtin.file:
    path: "{{ vllm_hf_hub_cache }}"
    state: directory
    owner: "{{ vllm_venv_owner }}"
    group: "{{ vllm_venv_owner }}"
    mode: "0755"
  become: true

- name: Report models to be staged this run
  ansible.builtin.debug:
    msg: "{{ vllm_enabled_models | map(attribute='id') | list }}"

- name: Check for existing snapshot dir per enabled model
  ansible.builtin.stat:
    path: "{{ vllm_hf_hub_cache }}/models--{{ item.hf_repo | regex_replace('/', '--') }}/snapshots"
  loop: "{{ vllm_enabled_models }}"
  loop_control:
    label: "{{ item.id }}"
  register: vllm_model_snapshot_stat

- name: Download model repo(s) not yet staged
  ansible.builtin.command:
    cmd: >-
      {{ vllm_venv_path }}/bin/hf download {{ item.item.hf_repo }}
      --cache-dir {{ vllm_hf_hub_cache }}
  become: true
  become_user: "{{ vllm_venv_owner }}"
  environment:
    HF_HUB_ENABLE_HF_TRANSFER: "0"
  loop: "{{ vllm_model_snapshot_stat.results }}"
  loop_control:
    label: "{{ item.item.id }}"
  when: not (item.stat.exists | default(false)) or (item.stat.isdir | default(false) and item.stat.size == 0)
  register: vllm_model_download
  # Full-size model pulls (9-18GB for 32B AWQ) can take a long time on
  # homelab bandwidth — allow up to 1 hour per model.
  async: 3600
  poll: 30

- name: Re-stat snapshot dirs to confirm download landed
  ansible.builtin.stat:
    path: "{{ vllm_hf_hub_cache }}/models--{{ item.hf_repo | regex_replace('/', '--') }}/snapshots"
  loop: "{{ vllm_enabled_models }}"
  loop_control:
    label: "{{ item.id }}"
  register: vllm_model_snapshot_verify

- name: Fail if any enabled model failed to stage
  ansible.builtin.fail:
    msg: "Model {{ item.item.id }} ({{ item.item.hf_repo }}) is not present at {{ vllm_hf_hub_cache }} after download step."
  loop: "{{ vllm_model_snapshot_verify.results }}"
  loop_control:
    label: "{{ item.item.id }}"
  when: not (item.stat.exists | default(false))

- name: Compute on-disk size of each staged model (sanity check, not a strict checksum)
  ansible.builtin.command:
    cmd: "du -sh {{ vllm_hf_hub_cache }}/models--{{ item.hf_repo | regex_replace('/', '--') }}"
  loop: "{{ vllm_enabled_models }}"
  loop_control:
    label: "{{ item.id }}"
  register: vllm_model_size
  changed_when: false

- name: Report staged model sizes
  ansible.builtin.debug:
    msg: "{{ item.stdout }}"
  loop: "{{ vllm_model_size.results }}"
  loop_control:
    label: "{{ item.item.id }}"