homelab/ansible/roles/llm-inference-multimodel/tasks/models.yml

---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/tasks/models.yml
# DESCRIPTION: Phase 1 — ensure the production Qwen GGUF is present on disk.
#              Idempotent: reuses the stat + size-threshold guard pattern.
#
#              HISTORY (2026-08-06): This file previously downloaded Phi-4-14B
#              (aux, port 8000) and Mistral-Small-24B (tool-calling, port 8001).
#              Both were retired on 2026-08-06 when the deployment was
#              consolidated to a single model (Qwen2.5-14B-Instruct-1M, port
#              8002). The download tasks and VRAM co-residency logic were
#              removed from this file; see git log if a rollback needs them.
#
#              HISTORY (2026-08-07): Qwen2.5-14B-Instruct-1M was superseded by
#              Qwen3.6-35B-A3B-UD-Q4_K_S (see task t_2ffc0f63). The model
#              was downloaded out-of-band (direct wget per t_2ffc0f63 runbook)
#              rather than via this role's get_url pattern. The path and
#              variables below are updated to reflect the current production
#              model; the download task is a no-op if the file is already
#              present (which it is on astro-orbiter as of 2026-08-07+).
#
#              2026-08-12 (t_0cca74a2): Cleaned up stale Phi-4/Mistral tasks
#              that referenced undefined variables after the Aug 2026
#              consolidation. models.yml now only manages the Qwen3.6-35B
#              model that is the sole production model.
# ------------------------------------------------------------------------------

- name: Create models directory
  ansible.builtin.file:
    path: "{{ llm_models_dir }}"
    state: directory
    owner: "{{ llm_service_user }}"
    group: "{{ llm_service_user }}"
    mode: "0755"
  become: true

# --- Production model: Qwen3.6-35B-A3B-UD-Q4_K_S (port 8002 / router :8003) -

- name: Check if Qwen3.6-35B GGUF is present on disk
  ansible.builtin.stat:
    path: "{{ llm_qwen_model_path }}"
  register: llm_qwen_model_stat

- name: Report Qwen model presence (model was downloaded out-of-band via t_2ffc0f63)
  ansible.builtin.debug:
    msg: >-
      Qwen model at {{ llm_qwen_model_path }}:
      exists={{ llm_qwen_model_stat.stat.exists | default(false) }},
      size={{ (llm_qwen_model_stat.stat.size | default(0) | int / 1073741824) | round(2) }}GB
  when: llm_qwen_model_stat.stat.exists | default(false)

- name: WARN — Qwen model GGUF not found at expected path
  ansible.builtin.debug:
    msg: >-
      WARNING: Qwen model NOT found at {{ llm_qwen_model_path }}.
      This model was originally downloaded via task t_2ffc0f63 (direct wget,
      not via this role's get_url). If the file is missing, re-download it
      manually or add a get_url task here with the correct HuggingFace URL.
      Expected URL (bartowski UD-Q4_K_S):
      https://huggingface.co/bartowski/Qwen3.6-35B-A3B-UD-Q4_K_S-GGUF/resolve/main/Qwen3.6-35B-A3B-UD-Q4_K_S.gguf
  when: not (llm_qwen_model_stat.stat.exists | default(false))

# --- Staged GGUF models (data-driven, idempotent) ----------------------------
# Ensure every entry in llm_staged_models is present in llm_models_dir with the
# EXACT expected byte size. When present AND size matches, this is a pure
# no-op: no download, no service touch. When a genuine new/mismatched GGUF is
# detected, it is downloaded + ownership/mode corrected and the router restart
# handler is notified so the llama.cpp router re-discovers the models_dir.
# Driven entirely by inventory vars (host_vars) — nothing hardcoded here, so
# adding a future model = append to llm_staged_models in host_vars.
- name: Stage data-driven GGUF models into {{ llm_models_dir }}
  ansible.builtin.include_tasks: stage_model.yml
  loop: "{{ llm_staged_models | default([]) }}"
  loop_control:
    loop_var: staged_model
  tags: [models]

# --- Chat template overrides ---------------------------------------------------
# Deploy per-model chat template files used by llama-server via chat-template-file.
# These are static files dropped into {{ llm_models_dir }}/templates/.
# t_664289a0: qwen3-no-think.jinja — Qwen3 template with enable_thinking=false
#   hardcoded. Used by [Qwen3-8B-Q4_K_M-no_think] in the router preset INI and
#   the llama-swap config. The companion [Qwen3-8B-Q4_K_M] section uses the GGUF's
#   baked-in template (thinking ON by default).
- name: Ensure chat template directory exists at {{ llm_models_dir }}/templates
  ansible.builtin.file:
    path: "{{ llm_models_dir }}/templates"
    state: directory
    owner: "{{ llm_service_user }}"
    group: "{{ llm_service_user }}"
    mode: "0755"
  become: true
  tags: [models, chat_templates]

- name: Deploy qwen3-no-think.jinja (thinking=false hard-switch for Qwen3-8B no_think variant)
  ansible.builtin.template:
    src: qwen3-no-think.jinja.j2
    dest: "{{ llm_models_dir }}/templates/qwen3-no-think.jinja"
    owner: "{{ llm_service_user }}"
    group: "{{ llm_service_user }}"
    mode: "0644"
  become: true
  tags: [models, chat_templates]