---
# Is each systemd-deployed service actually running?
#
# Every 5 minutes, with an 11-minute Gatus heartbeat - one missed run before
# it alarms, so a reboot or a slow check does not page anyone, but a host that
# stops reporting does.
#
# This closes the gap that let a real bug run unnoticed: a backup script left
# forgejo, lnbits, headscale and memos stopped, and NOTHING caught it. The dumps
# exited 0, the artefacts were correct, the deploy said failed=0, and liveness
# only proves the HOST is up - not that anything on it is serving.
#
# One endpoint PER UNIT, not per host. A host running four services needs four
# endpoints, or a single red light says "something on vipy is down" without
# saying which - and that is the question you actually have at 3am. But only ONE
# timer per host: the check iterates that host's units and pushes a result for
# each, the same way check-backups.sh reports per source. Four units on vipy
# would otherwise mean four scripts, four services and four timers.
#
# Which units each host runs is in host_vars/<host>/main.yml as
# monitored_services, because "what runs here" is a property of the machine.
#
# Keys are host-qualified because unit names collide - caddy runs on four
# machines. Gatus computes sanitize(group)_sanitize(name), so group "services"
# and name "vipy/caddy" give services_vipy-caddy.

# ─────────────────────────────────────────────────────────────────────────────
# Register one endpoint per unit. Runs first: Gatus reloads within 30s, and the
# host play above takes minutes, so every endpoint exists before its first push.
# ─────────────────────────────────────────────────────────────────────────────
# ─────────────────────────────────────────────────────────────────────────────
# Alerting thresholds, and why they differ by check type.
#
# `failure-threshold` counts CONSECUTIVE failures, but "consecutive" means a
# different amount of wall-clock time per check:
#
#   push/heartbeat endpoints   a failure is produced once per heartbeat window
#   pulled endpoints           a failure is produced once per interval
#
# So the default of 3 would mean 33 minutes on an 11m heartbeat and over a day
# on a 7h one - and the heartbeat window ALREADY encodes the tolerance. An 11m
# window on a 5-minute push is precisely "one missed push forgiven"; stacking a
# threshold of 3 on top triples a tolerance that was already chosen.
#
# Hence: push endpoints alert on the FIRST heartbeat failure. Pulled endpoints
# have no built-in tolerance, so the threshold is where it belongs for them.
# ─────────────────────────────────────────────────────────────────────────────
- name: Register the service checks with Gatus
  hosts: observability
  become: yes

  tasks:
    # Two plain steps rather than one clever expression: first collect which
    # units each host declares, then flatten that into endpoints.
    - name: Collect the units each host declares
      ansible.builtin.set_fact:
        host_units: "{{ host_units | default([]) + [{'host': item, 'units': hostvars[item].monitored_services}] }}"
      loop: "{{ groups['managed'] | sort }}"
      when: hostvars[item].monitored_services | default([]) | length > 0

    - name: Build one endpoint per unit
      ansible.builtin.set_fact:
        service_endpoints: "{{ service_endpoints | default([]) + [{
          'name': (item.0.host | lower | regex_replace('[/_.,# +&]', '-')) ~ '/' ~ item.1,
          'group': 'services',
          'token': gatus_push_tokens[item.0.host],
          'heartbeat': '11m'}] }}"
      loop: "{{ host_units | subelements('units') }}"

    - name: Register the service endpoints
      ansible.builtin.include_role:
        name: gatus_endpoint
      vars:
        gatus_endpoint_default_alerts:
          - type: signal
            # 1, not 3: the heartbeat window is the tolerance. See the note above.
            failure-threshold: 1
            success-threshold: 2
            send-on-resolved: true
            minimum-reminder-interval: 6h
        gatus_endpoint_name: services
        gatus_endpoint_external: "{{ service_endpoints }}"

- name: Monitor systemd services on every host that has them
  hosts: managed
  become: yes
  vars:
    gatus_api: "https://{{ subdomains.gatus }}.{{ root_domain }}/api/v1/endpoints"
    host_key: "{{ inventory_hostname | lower | regex_replace('[/_.,# +&]', '-') }}"

  tasks:
    - name: Is every deployed service running?
      ansible.builtin.include_role:
        name: healthcheck
      vars:
        healthcheck_name: service-health
        healthcheck_description: "systemd services on {{ inventory_hostname }}"
        healthcheck_check: systemd-units
        healthcheck_units: "{{ monitored_services }}"
        healthcheck_units_key_prefix: "services_{{ host_key }}"
        healthcheck_interval: "5min"
        healthcheck_boot_delay: "2min"
        # The per-unit results go to keys under this collection; the role's own
        # single-result push is unused here, so only the base is set.
        healthcheck_push_base: "{{ gatus_api }}"
        healthcheck_push_token: "{{ gatus_push_tokens[inventory_hostname] }}"
      when: monitored_services | default([]) | length > 0