personal_infra/ansible/roles/gatus/defaults/main.yml

---
# Gatus, deployed the way upstream distributes it: the container image.
#
# Upstream publishes NO binary release assets - the image is the only artefact
# they ship, and therefore the only artefact they test. Building from source is
# possible (`go build` alone is enough; the Vue dashboard is compiled in via
# `//go:embed static`, and CGO_ENABLED=0 works because the sqlite driver is
# pure-Go modernc.org/sqlite) but it produces a binary upstream never ran, and
# it means a full compile of the AWS SDK and gRPC on the smallest box in the
# estate.

# ── Image ────────────────────────────────────────────────────────────────────
gatus_version: "v5.36.0"
# Pinned by DIGEST, not by tag. A tag is mutable - `v5.36.0` can be repushed -
# so pinning the tag alone is a weaker promise than it looks. The digest is the
# content address: if it resolves, it is byte-for-byte the image reviewed here.
# Both must be updated together; the tag is kept only so humans can read it.
gatus_image_digest: "sha256:c5f210d095fa78e6efaa20ffeb14803f2ba4f10615e16a6d12087697149617f0"
gatus_image: "ghcr.io/twin/gatus@{{ gatus_image_digest }}"

# ── Paths (host side) ────────────────────────────────────────────────────────
gatus_dir: /opt/gatus
gatus_config_dir: "{{ gatus_dir }}/config"
gatus_data_dir: "{{ gatus_dir }}/data"

# Gatus merges every *.yaml under GATUS_CONFIG_PATH and its subdirectories:
# maps deep-merge, lists append. That is why this role ships a config DIRECTORY
# rather than one file - each service contributes its own endpoint file, the
# same way each service contributes a vhost through `caddy_site`.
#
# Primitives must be defined exactly once across all files or the merge is
# ambiguous, so everything that is not a list lives in the base file and
# nowhere else.
gatus_base_config_file: "00-base.yaml"
gatus_endpoints_dir: "{{ gatus_config_dir }}/endpoints"

# ── Identity ─────────────────────────────────────────────────────────────────
# The image is FROM scratch, so it has no /etc/passwd and no user to drop to by
# name. Run it by numeric uid/gid instead, and own the data volume to match.
gatus_uid: 10001
gatus_gid: 10001

# ── Web ──────────────────────────────────────────────────────────────────────
gatus_port: 8080
# HOST-side address the container's port is published on. Gatus itself always
# binds 0.0.0.0 inside the container - see the note in config.yaml.j2. Never
# publish this on 0.0.0.0: the external-endpoint push API shares the dashboard's
# listener, and Caddy is what should be in front of both.
gatus_bind_address: "127.0.0.1"
# Pass-through, the same shape as gatus_alerting: whatever is set here is
# rendered verbatim under `ui:`, so every option upstream supports is reachable
# without adding a variable per key. See config/ui/ui.go for the full set -
# title, description, header, dashboard-heading/subheading, logo, link, favicon,
# buttons, custom-css, dark-mode, default-sort-by, default-filter-by.
gatus_ui:
  title: "Status"
  header: "Status"
  # Group by default. The dashboard's own groupByGroup toggle starts OFF and
  # remembers per browser in localStorage, so without this the ten groups render
  # as one flat list for anyone who has not clicked it.
  default-sort-by: group

# ── Storage ──────────────────────────────────────────────────────────────────
# sqlite, not memory: history has to survive a restart, or the dashboard lies
# about uptime after every deploy. Path is INSIDE the container.
gatus_storage_type: sqlite
gatus_storage_path: "/data/gatus.db"
gatus_storage_caching: true

# Per-endpoint row caps. Gatus bounds the database by COUNT, not by time, and
# trims inline on insert (storage/store/sql/sql.go, InsertEndpointResult) - so
# there is no retention job to write and no way for this to fill a disk.
#
# History depth is therefore a function of check frequency, not of days:
# 900 results is ~3 days of a 5-minute liveness check, and ~2.5 years of a daily
# disk check. Upstream's default is 100, which would have been 8 hours of
# liveness - not enough to still see a weekend incident on Monday.
#
# Note the uptime table is separate and its 30-day retention is hard-coded
# upstream (uptimeRetention), so uptime percentages top out at 30 days whatever
# this is set to.
gatus_storage_max_results: 900
gatus_storage_max_events: 50

# ── Alerting ─────────────────────────────────────────────────────────────────
# Pass-through: rendered verbatim under `alerting:`, so any provider Gatus
# supports works without touching this role. Empty means "check and record,
# alert nowhere" - valid, and the default until a provider is chosen.
gatus_alerting: {}
gatus_default_alerts: []

# ── Security ─────────────────────────────────────────────────────────────────
#   gatus_basic_auth: {username: admin, password-bcrypt-base64: "..."}
gatus_basic_auth: {}

gatus_maintenance: {}

# Keep serving the previous config if a contributed endpoint file is malformed,
# instead of panicking. See the note in config.yaml.j2.
gatus_skip_invalid_config_update: true
gatus_log_level: INFO

# ── Self-check ───────────────────────────────────────────────────────────────
# Gatus panics on a config with no endpoints, so the role always ships one.
# Turning this off is only safe once another file in endpoints/ provides one.
gatus_self_check: true

# ── ICMP ─────────────────────────────────────────────────────────────────────
# Gatus supports icmp:// endpoints. Raw ICMP needs CAP_NET_RAW, which the
# container would get free only if it ran as root; it does not. Set false if
# you never use icmp:// checks and want the capability dropped entirely.
gatus_allow_icmp: true

# ── Shared network ───────────────────────────────────────────────────────────
# Gatus runs in a container, so the HOST's loopback is not reachable from it.
# Anything Gatus must talk to locally - the Signal API that sends its alerts -
# has to be on a shared docker network and addressed by service name.
gatus_network: monitoring