tftsr_ai/playbooks/04_models.yml

---
# playbooks/04_models.yml
# Pull and register Ollama models based on benchmark selection

- name: "Models | Pull and register Ollama models"
  hosts: ai_server
  become: true
  gather_facts: true
  tags:
    - models
  vars:
    model_selection_file: "{{ playbook_dir }}/../benchmarks/results/model_selection.json"
    modelfiles_dir: /mnt/ai_data/ollama_models/modelfiles
    slot4_model: ""   # legacy override kept for backwards compatibility
    slot5_model: ""   # overrides slot5_general_rotate
    slot6_model: ""   # overrides slot6_coding_rotate
    ollama_api_key: "{{ lookup('community.hashi_vault.hashi_vault', vault_secret_prefix ~ '/ollama:api_key token=' ~ lookup('ansible.builtin.file', vault_token_file) ~ ' url=' ~ vault_url) }}"

  tasks:
    # ── Load benchmark results ───────────────────────────────────────
    - name: "Models | Read model_selection.json from control node"
      ansible.builtin.slurp:
        src: "{{ model_selection_file }}"
      delegate_to: localhost
      become: false
      register: model_selection_raw
      tags:
        - models-load

    - name: "Models | Parse model selection data"
      ansible.builtin.set_fact:
        model_selection: "{{ model_selection_raw.content | b64decode | from_json }}"
      tags:
        - models-load

    - name: "Models | Apply slot4 override if provided"
      ansible.builtin.set_fact:
        model_selection: "{{ model_selection | combine({'slot4_coding': slot4_model}) }}"
      when: slot4_model | length > 0
      tags:
        - models-load

    - name: "Models | Apply slot5 override if provided"
      ansible.builtin.set_fact:
        model_selection: "{{ model_selection | combine({'slot5_general_rotate': slot5_model}) }}"
      when: slot5_model | length > 0
      tags:
        - models-load

    - name: "Models | Apply slot6 override if provided"
      ansible.builtin.set_fact:
        model_selection: "{{ model_selection | combine({'slot6_coding_rotate': slot6_model}) }}"
      when: slot6_model | length > 0
      tags:
        - models-load

    - name: "Models | Display selected models"
      ansible.builtin.debug:
        msg:
          - "=== Node 1 — General (port 11434) ==="
          - "Slot 1 (locked):  {{ model_selection.slot1_general }}"
          - "Slot 2 (locked):  {{ model_selection.slot2_general }}"
          - "Slot 5 (rotate):  {{ model_selection.slot5_general_rotate | default('none') }}"
          - "=== Node 0 — Coding (port 11435) ==="
          - "Slot 3 (locked):  {{ model_selection.slot3_coding }}"
          - "Slot 4 (locked):  {{ model_selection.slot4_coding }}"
          - "Slot 6 (rotate):  {{ model_selection.slot6_coding_rotate | default('none') }}"
      tags:
        - models-load

    # ── Pull models ──────────────────────────────────────────────────
    - name: "Models | Get currently installed models"
      ansible.builtin.command: ollama list
      changed_when: false
      register: current_models
      tags:
        - models-pull

    - name: "Models | Set installed models list"
      ansible.builtin.set_fact:
        installed_model_names: >-
          {{ current_models.stdout_lines[1:] |
             default([]) |
             map('split') |
             map('first') |
             list }}
      tags:
        - models-pull

    - name: "Models | Pull slot models if not already present"
      ansible.builtin.command: "ollama pull {{ item }}"
      loop:
        - "{{ model_selection.slot1_general }}"
        - "{{ model_selection.slot2_general }}"
        - "{{ model_selection.slot5_general_rotate | default('none') }}"
        - "{{ model_selection.slot3_coding }}"
        - "{{ model_selection.slot4_coding }}"
        - "{{ model_selection.slot6_coding_rotate | default('none') }}"
      when:
        - item | length > 0
        - item != 'none'
        - item not in installed_model_names
      changed_when: true
      loop_control:
        label: "Pulling {{ item }}"
      tags:
        - models-pull

    - name: "Models | Pull baseline models if not already present"
      ansible.builtin.command: "ollama pull {{ item }}"
      loop: "{{ baseline_models }}"
      when: item not in installed_model_names
      changed_when: true
      loop_control:
        label: "Pulling {{ item }}"
      tags:
        - models-pull

    # ── Create Modelfiles ────────────────────────────────────────────
    - name: "Models | Create modelfiles directory"
      ansible.builtin.file:
        path: "{{ modelfiles_dir }}"
        state: directory
        mode: "0755"
        owner: root
        group: root
      tags:
        - models-modelfile

    - name: "Models | Template coder-128k Modelfile"
      ansible.builtin.copy:
        content: |
          FROM {{ model_selection.slot3_coding }}
          PARAMETER num_ctx 32768
          SYSTEM You are an expert coding assistant. You write clean, efficient, well-documented code. Always include type hints and follow best practices.
        dest: "{{ modelfiles_dir }}/Modelfile.coder-128k"
        mode: "0644"
      tags:
        - models-modelfile

    - name: "Models | Template coder-32k Modelfile"
      ansible.builtin.copy:
        content: |
          FROM {{ model_selection.slot4_coding }}
          PARAMETER num_ctx 32768
          SYSTEM You are an expert coding assistant. You write clean, efficient, well-documented code. Always include type hints and follow best practices.
        dest: "{{ modelfiles_dir }}/Modelfile.coder-32k"
        mode: "0644"
      when:
        - model_selection.slot4_coding | length > 0
        - model_selection.slot4_coding != 'none'
      tags:
        - models-modelfile

    - name: "Models | Template coder-rotate Modelfile"
      ansible.builtin.copy:
        content: |
          FROM {{ model_selection.slot6_coding_rotate }}
          PARAMETER num_ctx 32768
          SYSTEM You are an expert coding assistant. You write clean, efficient, well-documented code. Always include type hints and follow best practices.
        dest: "{{ modelfiles_dir }}/Modelfile.coder-rotate"
        mode: "0644"
      when:
        - model_selection.slot6_coding_rotate | default('') | length > 0
        - model_selection.slot6_coding_rotate | default('none') != 'none'
      tags:
        - models-modelfile

    - name: "Models | Template llama-family Modelfile"
      ansible.builtin.copy:
        content: |
          FROM llama3.2:3b
          PARAMETER num_ctx 8192
          SYSTEM You are a helpful, friendly family assistant. Provide safe, age-appropriate responses suitable for all family members.
        dest: "{{ modelfiles_dir }}/Modelfile.llama-family"
        mode: "0644"
      tags:
        - models-modelfile

    - name: "Models | Template gemma-family Modelfile"
      ansible.builtin.copy:
        content: |
          FROM llama3.1:8b
          PARAMETER num_ctx 8192
          SYSTEM You are a helpful, friendly family assistant. Provide safe, age-appropriate responses suitable for all family members.
        dest: "{{ modelfiles_dir }}/Modelfile.gemma-family"
        mode: "0644"
      tags:
        - models-modelfile

    # ── Register models ──────────────────────────────────────────────
    - name: "Models | Register custom models with Ollama"
      ansible.builtin.command: "ollama create {{ item.name }} -f {{ modelfiles_dir }}/{{ item.file }}"
      loop:
        - { name: "coder-128k",   file: "Modelfile.coder-128k" }
        - { name: "coder-32k",    file: "Modelfile.coder-32k",    slot: "{{ model_selection.slot4_coding }}" }
        - { name: "coder-rotate", file: "Modelfile.coder-rotate", slot: "{{ model_selection.slot6_coding_rotate | default('none') }}" }
        - { name: "llama-family", file: "Modelfile.llama-family" }
        - { name: "gemma-family", file: "Modelfile.gemma-family" }
      when: item.slot is not defined or (item.slot | length > 0 and item.slot != 'none')
      changed_when: true
      loop_control:
        label: "Creating {{ item.name }}"
      tags:
        - models-register

    # ── Warmup service ───────────────────────────────────────────────
    - name: "Models | Template warmup script"
      ansible.builtin.template:
        src: "{{ playbook_dir }}/../templates/ollama/warmup.sh.j2"
        dest: /usr/local/bin/ollama-warmup.sh
        mode: "0755"
        owner: root
        group: root
      tags:
        - models-warmup

    - name: "Models | Template warmup systemd service"
      ansible.builtin.template:
        src: "{{ playbook_dir }}/../templates/systemd/ollama-warmup.service.j2"
        dest: /etc/systemd/system/ollama-warmup.service
        mode: "0644"
        owner: root
        group: root
      tags:
        - models-warmup

    - name: "Models | Reload systemd daemon"
      ansible.builtin.systemd:
        daemon_reload: true
      tags:
        - models-warmup

    - name: "Models | Enable and start warmup service"
      ansible.builtin.systemd:
        name: ollama-warmup
        enabled: true
        state: started
      tags:
        - models-warmup

    # ── Node0 warmup service ─────────────────────────────────────────
    - name: "Models | Template node0 warmup script"
      ansible.builtin.template:
        src: "{{ playbook_dir }}/../templates/ollama/warmup-node0.sh.j2"
        dest: /usr/local/bin/ollama-warmup-node0.sh
        mode: "0755"
        owner: root
        group: root
      tags:
        - models-warmup

    - name: "Models | Template node0 warmup systemd service"
      ansible.builtin.template:
        src: "{{ playbook_dir }}/../templates/systemd/ollama-warmup-node0.service.j2"
        dest: /etc/systemd/system/ollama-warmup-node0.service
        mode: "0644"
        owner: root
        group: root
      tags:
        - models-warmup

    - name: "Models | Enable and start node0 warmup service"
      ansible.builtin.systemd:
        name: ollama-warmup-node0
        enabled: true
        state: started
        daemon_reload: true
      tags:
        - models-warmup