---
# One health check: a script, a systemd service, a timer, and an optional push.
#
# The exit code is the answer and systemd keeps it:
#     systemctl is-failed <name>-healthcheck.service
# Reporting anywhere else is optional and generic. Point healthcheck_push_url at
# Gatus, or at whatever replaces it, or at nothing.

healthcheck_name: ""                 # e.g. disk-usage -> disk-usage-healthcheck
healthcheck_description: ""

# The check itself. Pick ONE:
#   healthcheck_check: a template under templates/checks/ (without .sh.j2)
#   healthcheck_command: a shell one-liner that exits 0 for healthy
healthcheck_check: ""
healthcheck_command: ""

# systemd timer. OnUnitActiveSec unless healthcheck_on_calendar is set.
healthcheck_interval: "5min"
healthcheck_on_calendar: ""
healthcheck_boot_delay: "2min"

# ── Reporting ────────────────────────────────────────────────────────────────
# Gatus external endpoints:
#   POST {url}?success=true|false&error=...
#   Authorization: Bearer {token}
# Empty url = check and log only, which is a valid state and not an error.
healthcheck_push_url: ""
healthcheck_push_token: ""

# Some checks report MORE THAN ONE result - a host with four systemd services
# needs four endpoints, or a single red light cannot tell you which one died.
# Those set healthcheck_push_base to the endpoints COLLECTION and the check body
# appends each key itself, the same way check-backups.sh reports per source.
healthcheck_push_base: ""

# Units for the systemd-units check. Each becomes its own Gatus endpoint.
healthcheck_units: []
# Prefix for the per-unit endpoint keys, e.g. "services_vipy" -> services_vipy-caddy.
healthcheck_units_key_prefix: ""

healthcheck_script_dir: /usr/local/bin
healthcheck_log_dir: /var/log/healthchecks

# Per-check knobs, consumed by the templates under checks/
healthcheck_disk_threshold: 85       # percent
healthcheck_cpu_temp_threshold: 80   # celsius
healthcheck_zfs_pool: ""
# ZFS degrades badly once a pool passes roughly 80% - allocation gets slow and
# fragmentation becomes hard to undo, and unlike a normal filesystem you cannot
# simply delete your way back to good performance. So this alarms well before
# the pool is actually out of space.
healthcheck_zfs_capacity_threshold: 80
healthcheck_ups_name: ""