counterweight
3be5e7934c
99stack is prepaid: when the balance runs out the servers stop. A pulled check on the account API alerts when billing.secondsdue - the provider's own runway at current spend - drops under 14 days: checked every 6h, reminding every 24h. gatus_endpoint gains a `headers` field for APIs behind a credential. The vault gains ninetyninestack_api_token (account-wide; 99stack has no read-only scope) and gatus_push_tokens.arbret, used by the next commit. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
59 lines
2.7 KiB
YAML
59 lines
2.7 KiB
YAML
---
|
|
# One invocation writes ONE file into Gatus's endpoints directory. Gatus merges
|
|
# every *.yaml under GATUS_CONFIG_PATH and appends lists, so each caller owns
|
|
# its own file and they compose without coordinating - the same shape as
|
|
# caddy_site, where each service contributes its own vhost.
|
|
|
|
# Filename stem: <name>.yaml
|
|
gatus_endpoint_name: ""
|
|
|
|
# PULLED endpoints - Gatus makes the request and evaluates conditions.
|
|
# - {name, group, url, interval, conditions: [...], alerts: [...]}
|
|
#
|
|
# A DNS check adds `dns: {query-type, query-name}` - and note that for those,
|
|
# `url` is the RESOLVER to ask, not the name being looked up.
|
|
# An API behind a credential adds `headers: {Authorization: ...}`.
|
|
# A domain-expiry check is just `url: <domain>` with a [DOMAIN_EXPIRATION]
|
|
# condition; it uses WHOIS/RDAP and needs no scheme.
|
|
gatus_endpoint_pulled: []
|
|
|
|
# EXTERNAL endpoints - the host pushes its own result. Gatus never reaches out,
|
|
# which is what makes this work for machines behind NAT and for state that has
|
|
# no pollable surface at all (disk usage, ZFS health, UPS mains).
|
|
#
|
|
# - {name, group, token, heartbeat, alerts: [...]}
|
|
#
|
|
# `heartbeat` is the important one: if nothing reports within that window Gatus
|
|
# alerts. That is what makes a push check detect its own failure - a dead timer
|
|
# looks exactly like a dead host, which is the correct reading.
|
|
gatus_endpoint_external: []
|
|
|
|
# Where the files live. Matches roles/gatus.
|
|
gatus_config_dir: /opt/gatus/config
|
|
gatus_endpoints_dir: "{{ gatus_config_dir }}/endpoints"
|
|
gatus_gid: 10001
|
|
|
|
# Alerts attached to every endpoint in this file that does not specify its own.
|
|
#
|
|
# Gatus's provider-level `default-alert` only supplies DEFAULTS - an endpoint
|
|
# still has to opt in with `alerts: - type: signal` or it alerts on nothing at
|
|
# all. With ~90 endpoints that cannot be written by hand, so it is applied here.
|
|
#
|
|
# failure-threshold is set by the CALLER, because the right value depends on the
|
|
# check's cadence and there is no single correct default. See the note in
|
|
# infra/400_host_monitoring.yml.
|
|
gatus_endpoint_default_alerts: []
|
|
|
|
# UI options applied to every PULLED endpoint that does not set its own.
|
|
#
|
|
# Only pulled endpoints can carry this - an external (push) endpoint has no `ui`
|
|
# field at all, because it has no conditions to display.
|
|
#
|
|
# Note that every hide-* option already defaults to false upstream, so there is
|
|
# nothing to un-hide. The one setting that genuinely shows MORE is
|
|
# resolve-successful-conditions: by default a failing check displays the real
|
|
# value - "[STATUS] (502) == 200" - while a passing one drops it and shows only
|
|
# "[STATUS] == 200". Turning it on resolves both, so a healthy DNS check shows
|
|
# the IP it actually resolved rather than just the assertion.
|
|
gatus_endpoint_default_ui:
|
|
resolve-successful-conditions: true
|