ansible/playbooks/service_check.yml

---
# Verifies the critical services listed per host in the inventory
# (critical_services) and optionally starts any that are stopped. Services
# found not running are sent as one Telegram message per run when Telegram
# credentials are present.
#
# Extra vars (optional):
#   restart_stopped    - default false; when true, start services found stopped
#   telegram_bot_token - or environment variable TELEGRAM_BOT_TOKEN
#   telegram_chat_id   - or environment variable TELEGRAM_CHAT_ID

- name: Check Host Availability
  hosts: ubuntu:rocky
  gather_facts: false
  ignore_unreachable: true

  tasks:
    - name: Ping hosts to check availability
      ansible.builtin.ping:
      register: ping_result
      ignore_errors: true
      ignore_unreachable: true

    - name: Add reachable hosts to group
      ansible.builtin.group_by:
        key: reachable_hosts
      when: ping_result is reachable and ping_result is succeeded

    - name: Report offline hosts
      ansible.builtin.debug:
        msg: "{{ inventory_hostname }} - OFFLINE"
      when: ping_result is unreachable or ping_result is failed
      delegate_to: localhost

- name: Service Check
  hosts: reachable_hosts
  become: true
  gather_facts: false

  vars:
    restart_stopped: false

  tasks:
    - name: Gather service facts
      ansible.builtin.service_facts:

    - name: Evaluate critical services
      ansible.builtin.set_fact:
        service_states: >-
          {{ service_states | default([])
             + [{'name': item, 'state': (ansible_facts.services[item ~ '.service'].state | default('not-found'))}] }}
      loop: "{{ critical_services | default([]) }}"

    - name: Print report
      ansible.builtin.debug:
        msg: |
          ======================================================
           HOST: {{ inventory_hostname }} ({{ ansible_host }})
          ======================================================
          {% if service_states | default([]) | length == 0 %}
           no critical services defined in inventory
          {% else %}
          {% for svc in service_states %}
           {{ '%-24s' | format(svc.name) }} {{ 'RUNNING' if svc.state == 'running' else ('NOT FOUND' if svc.state == 'not-found' else svc.state | upper) }}
          {% endfor %}
          {% endif %}
          ======================================================

    - name: Warn on services that are not running
      ansible.builtin.debug:
        msg: "WARNING: {{ item.name }} is {{ 'not installed' if item.state == 'not-found' else item.state }} on {{ inventory_hostname }}"
      loop: "{{ service_states | default([]) }}"
      loop_control:
        label: "{{ item.name }}"
      when: item.state != 'running'

    - name: Start stopped services
      ansible.builtin.service:
        name: "{{ item.name }}"
        state: started
      loop: "{{ service_states | default([]) }}"
      loop_control:
        label: "{{ item.name }}"
      when:
        - restart_stopped | bool
        - item.state not in ['running', 'not-found']

- name: Telegram alert
  hosts: localhost
  connection: local
  gather_facts: false

  vars:
    restart_stopped: false
    telegram_bot_token: "{{ lookup('env', 'TELEGRAM_BOT_TOKEN') }}"
    telegram_chat_id: "{{ lookup('env', 'TELEGRAM_CHAT_ID') }}"
    telegram_configured: "{{ telegram_bot_token | length > 0 and telegram_chat_id | length > 0 }}"

  tasks:
    - name: Build alert text
      ansible.builtin.set_fact:
        alert_text: "{{ alert_body | default('', true) | trim }}"   # an empty template renders as None
      vars:
        alert_body: |-
          {% for h in groups['reachable_hosts'] | default([]) %}
          {% for svc in hostvars[h].service_states | default([]) if svc.state != 'running' %}
          {% set note = ' - start attempted' if (restart_stopped | bool and svc.state != 'not-found') else '' %}
          SERVICE {{ h }}: {{ svc.name }} {{ 'not installed' if svc.state == 'not-found' else svc.state }}{{ note }}
          {% endfor %}
          {% endfor %}

    - name: Nothing to alert
      ansible.builtin.debug:
        msg: "All critical services running - no alert"
      when: alert_text | length == 0

    - name: Print alerts when Telegram is not configured
      ansible.builtin.debug:
        msg: "ALERTS (Telegram not configured - set telegram_bot_token and telegram_chat_id):\n{{ alert_text }}"
      when:
        - alert_text | length > 0
        - not telegram_configured

    - name: Send Telegram alert
      ansible.builtin.uri:
        url: "https://api.telegram.org/bot{{ telegram_bot_token }}/sendMessage"
        method: POST
        body_format: json
        body:
          chat_id: "{{ telegram_chat_id }}"
          text: "Homelab service check {{ now().strftime('%Y-%m-%d %H:%M') }}\n{{ alert_text }}"
        status_code: [200]
      register: telegram_result
      failed_when: false
      no_log: true          # the bot token is part of the URL
      when:
        - alert_text | length > 0
        - telegram_configured

    - name: Telegram delivery status
      ansible.builtin.assert:
        that: telegram_result.status == 200
        fail_msg: "Telegram API returned {{ telegram_result.status }}: {{ telegram_result.json.description | default('no response') }}"
        success_msg: "Telegram alert sent ({{ alert_text.split('\n') | length }} line(s))"
      when: telegram_result is not skipped