tftsr_ai/playbooks/00_preflight.yml

---
# playbooks/00_preflight.yml
# Pre-flight checks: control-node dependencies, SSH/sudo connectivity, disk space, Ollama API health

- name: "Pre-flight | Control node dependencies"
  hosts: localhost
  connection: local
  gather_facts: false
  tags:
    - preflight
    - local-deps
  tasks:
    - name: "Preflight | Ensure hvac Python library is installed (required for Vault lookups)"
      ansible.builtin.pip:
        name: hvac
        state: present
      become: false

- name: "Pre-flight | Verify SSH and sudo access on all hosts"
  hosts: all
  gather_facts: true
  become: true
  tags:
    - preflight
    - connectivity
  tasks:
    - name: "Preflight | Confirm sudo privileges"
      ansible.builtin.command: whoami
      changed_when: false
      register: whoami_result

    - name: "Preflight | Assert running as root via sudo"
      ansible.builtin.assert:
        that:
          - whoami_result.stdout == "root"
        fail_msg: "sudo escalation failed on {{ inventory_hostname }}"
        success_msg: "sudo access confirmed on {{ inventory_hostname }}"

- name: "Pre-flight | Disk space checks on ai_server"
  hosts: ai_server
  gather_facts: false
  become: true
  tags:
    - preflight
    - disk
  tasks:
    - name: "Preflight | Get /mnt/ai_data mount info"
      ansible.builtin.command: df --output=avail -BG /mnt/ai_data
      changed_when: false
      register: ai_data_disk

    - name: "Preflight | Parse available disk space on /mnt/ai_data"
      ansible.builtin.set_fact:
        ai_data_avail_gb: "{{ ai_data_disk.stdout_lines[-1] | regex_replace('[^0-9]', '') | int }}"

    - name: "Preflight | Assert /mnt/ai_data has >= 500 GB free"
      ansible.builtin.assert:
        that:
          - ai_data_avail_gb | int >= 500
        fail_msg: >-
          CRITICAL: /mnt/ai_data on ai_server has only {{ ai_data_avail_gb }} GB free.
          At least 500 GB is required for AI models and application data.
        success_msg: "/mnt/ai_data has {{ ai_data_avail_gb }} GB free (>= 500 GB required)"

- name: "Pre-flight | Disk space checks on coredns_host"
  hosts: coredns_host
  gather_facts: false
  become: true
  tags:
    - preflight
    - disk
  tasks:
    - name: "Preflight | Get / mount info on coredns_host"
      ansible.builtin.command: df --output=avail -BG /
      changed_when: false
      register: root_disk

    - name: "Preflight | Parse available disk space on /"
      ansible.builtin.set_fact:
        root_avail_gb: "{{ root_disk.stdout_lines[-1] | regex_replace('[^0-9]', '') | int }}"

    - name: "Preflight | Assert / has >= 10 GB free on coredns_host"
      ansible.builtin.assert:
        that:
          - root_avail_gb | int >= 10
        fail_msg: >-
          CRITICAL: / on coredns_host has only {{ root_avail_gb }} GB free.
          At least 10 GB is required.
        success_msg: "/ has {{ root_avail_gb }} GB free (>= 10 GB required)"

- name: "Pre-flight | Ollama API health check on ai_server"
  hosts: ai_server
  gather_facts: false
  become: false
  tags:
    - preflight
    - ollama
  tasks:
    - name: "Preflight | Check Ollama API is responding"
      ansible.builtin.uri:
        url: "http://localhost:11434/api/tags"
        method: GET
        return_content: true
        status_code: 200
        timeout: 10
      register: ollama_health
      failed_when: false
      retries: 12
      delay: 5
      until: ollama_health.status is defined and ollama_health.status == 200

    - name: "Preflight | Assert Ollama API is healthy"
      ansible.builtin.assert:
        that:
          - ollama_health.status == 200
        fail_msg: >-
          CRITICAL: Ollama API is not responding on ai_server at http://localhost:11434/api/tags.
          HTTP status: {{ ollama_health.status | default('unreachable') }}.
          Ensure Ollama is installed and running before proceeding.
        success_msg: "Ollama API is healthy and responding on ai_server"

    - name: "Preflight | Display available Ollama models"
      ansible.builtin.debug:
        msg: "Ollama models available: {{ (ollama_health.json.models | default([])) | map(attribute='name') | list }}"
      when: ollama_health.status == 200