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

---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/tasks/verify.yml
# DESCRIPTION: Phase 4 (REVISED 2026-08-06) — consolidated deployment.
#              Only llama-server-qwen (Qwen2.5-14B-Instruct-1M, port 8002) is
#              started/enabled here now. The prior aux (Phi-4, port 8000) and
#              toolcall (Mistral-Small-24B, port 8001) start/smoke-test tasks
#              were removed along with those services — see git log for the
#              previous version of this file if a rollback needs them.
#
#              This is the ONLY phase that actually starts the qwen service
#              (systemd.yml deliberately does not). Enabling happens here too,
#              so a reboot brings it back.
# ------------------------------------------------------------------------------

- name: Gather service facts (systemd unit inventory) — ensure available even if discover.yml's tag wasn't selected
  ansible.builtin.service_facts:
  when: llm_existing_gemma_unit_found is not defined

- name: Determine whether a systemd unit matching the existing Gemma service exists (if not already known from discover.yml)
  ansible.builtin.set_fact:
    llm_existing_gemma_unit_found: "{{ (llm_existing_gemma_service_name_guess + '.service') in ansible_facts.services }}"
  when: llm_existing_gemma_unit_found is not defined

- name: Stop pre-existing Gemma llama-server before starting new instances (avoid double VRAM usage / OOM)
  ansible.builtin.systemd:
    name: "{{ llm_existing_gemma_service_name_guess }}"
    state: stopped
  become: true
  when: llm_existing_gemma_unit_found | default(false)

- name: Enable llama-server-qwen and start/restart based on Phase 2 unit-content change
  ansible.builtin.systemd:
    name: "{{ llm_qwen_service_name }}"
    state: "{{ 'restarted' if (llm_qwen_unit_deployed.changed | default(false)) else 'started' }}"
    enabled: true
    daemon_reload: true
  become: true
  when: llm_qwen_service_enabled | default(false)

- name: Wait for Qwen instance API to become available
  ansible.builtin.uri:
    url: "http://{{ llm_bind_address }}:{{ llm_qwen_port }}/health"
    status_code: 200
  register: llm_qwen_health
  retries: 24
  delay: 10
  until: llm_qwen_health.status == 200
  when: llm_qwen_service_enabled | default(false)

- name: Smoke-test — Qwen instance model listing + n_ctx verification
  ansible.builtin.uri:
    url: "http://{{ llm_bind_address }}:{{ llm_qwen_port }}/v1/models"
    status_code: 200
    return_content: true
  register: llm_qwen_models
  when: llm_qwen_service_enabled | default(false)

- name: Report Qwen instance served model + verified n_ctx
  ansible.builtin.debug:
    msg:
      - "Qwen (:{{ llm_qwen_port }}) serving: {{ llm_qwen_models.json.data | map(attribute='id') | list }}"
      - "Verified n_ctx (must be >= 64000, not just requested): {{ llm_qwen_models.json.data | map(attribute='meta') | map(attribute='n_ctx') | list }}"
  when: llm_qwen_service_enabled | default(false)

- name: Basic tool-calling smoke test — Qwen instance (this is the sole production model for both profiles)
  ansible.builtin.uri:
    url: "http://{{ llm_bind_address }}:{{ llm_qwen_port }}/v1/chat/completions"
    method: POST
    body_format: json
    body:
      model: "{{ llm_qwen_model_id }}"
      messages:
        - role: user
          content: "What is the weather in Chicago?"
      tools:
        - type: function
          function:
            name: get_weather
            description: Get weather for a city
            parameters:
              type: object
              properties:
                city:
                  type: string
              required:
                - city
    status_code: 200
    return_content: true
  register: llm_qwen_toolcall_smoke
  when: llm_qwen_service_enabled | default(false)

- name: Check GPU VRAM usage after Qwen instance is running
  ansible.builtin.command:
    cmd: nvidia-smi --query-gpu=memory.used,memory.total,utilization.gpu --format=csv,noheader
  register: llm_post_start_vram
  changed_when: false

- name: Report VRAM usage
  ansible.builtin.debug:
    msg:
      - "Measured (nvidia-smi):      {{ llm_post_start_vram.stdout }}"
      - "Qwen2.5-14B-Instruct-1M expected footprint: ~{{ llm_qwen_expected_vram_gb }}GB. Ports 8000/8001 are retired and no longer consume VRAM."

- name: Check for OOM-kill events related to llama-server in dmesg (best-effort, read-only)
  ansible.builtin.shell:
    cmd: "dmesg | grep -i 'llama-server' | grep -i -E 'oom|killed' || true"
  register: llm_oom_check
  changed_when: false
  become: true

- name: Report any OOM-kill findings
  ansible.builtin.debug:
    msg: >-
      {{ llm_oom_check.stdout if llm_oom_check.stdout | length > 0
         else 'No OOM-kill events found for llama-server in dmesg.' }}