#!/bin/bash # services/gatus.sh — Gatus status/uptime monitoring page. # Part of the modular post-install system (sourced by setup.sh). # # Can also be run standalone on any machine: # sudo bash gatus.sh # (Docker must already be installed when run standalone) # # Gatus polls endpoints (HTTP, TCP, DNS, ICMP) on a schedule and shows a # clean status dashboard. Config is hot-reloaded from gatus_config/config.yaml. # ── Standalone bootstrap ────────────────────────────────────────────────────── # Detected when the script is executed directly rather than sourced by setup.sh. # Sets up helpers and globals, then defers execution until after the function # definition at the bottom of this file. if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then [[ "$(id -u)" == "0" ]] || { echo "Run with sudo: sudo bash $0"; exit 1; } _SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" _COMMON="$_SELF_DIR/../lib/common.sh" if [[ -f "$_COMMON" ]]; then # Full repo present — use the real helpers (picks up ~/docker/.config too) # shellcheck source=../lib/common.sh source "$_COMMON" else # One-off copy — inline minimal stubs so the script works without the repo log_info() { echo -e "\033[0;34m[INFO]\033[0m $*"; } log_success() { echo -e "\033[0;32m[OK]\033[0m $*"; } log_warning() { echo -e "\033[1;33m[WARN]\033[0m $*"; } log_error() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; } require_docker() { command -v docker &>/dev/null || { log_error "Docker not found. Install it first:" log_error " curl -fsSL https://get.docker.com | sudo sh" return 1 } docker compose version &>/dev/null || { log_error "Docker Compose plugin missing:" log_error " sudo apt-get install -y docker-compose-plugin" return 1 } } ensure_docker_dir_ownership() { chown -R "$ACTUAL_USER:$ACTUAL_USER" "$@" 2>/dev/null || true } port_in_use() { local _port="$1" _proto="${2:-tcp}" local _flag="-tlnH" [ "$_proto" = "udp" ] && _flag="-ulnH" ss "$_flag" "sport = :${_port}" 2>/dev/null | grep -q . } find_free_port() { local _varname="$1" _port="$2" _proto="${3:-tcp}" while port_in_use "$_port" "$_proto"; do _port=$((_port + 1)) done eval "$_varname='$_port'" } # Match common.sh's eval-based pattern so local vars in install_* are set correctly prompt_text() { local _q="$1" _def="$2" _var="$3" _r [[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; } read -r -p " $_q " _r eval "$_var='${_r:-$_def}'" } prompt_yn() { local _q="$1" _def="$2" _var="$3" _r [[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; } read -r -p " $_q " _r eval "$_var='${_r:-$_def}'" } configure_caddy_for_service() { local _name="$1" _upstream="$2" _subdomain="$3" _extra="${4:-}" local _caddy_dir="$DOCKER_DIR/caddy" local _caddyfile="$_caddy_dir/Caddyfile" local _display_port="${_upstream##*:}" # Determine mode: local Caddy, remote Caddy, or none local _mode="none" [[ -d "$_caddy_dir" ]] && _mode="local" [[ -n "${CADDY_REMOTE_HOST:-}" ]] && [[ "$_mode" != "local" ]] && _mode="remote" [[ "$_mode" == "none" ]] && { log_info "Access $_name directly on port $_display_port." return 0 } echo "" local _do_caddy="" if [[ "$_mode" == "remote" ]]; then log_info "Remote Caddy configured (${CADDY_REMOTE_HOST})." log_info "A snippet file will be saved to ~/docker/caddy-snippets/." fi read -r -p " Configure Caddy reverse proxy for $_name? [y/N]: " _do_caddy [[ "${_do_caddy,,}" == "y" ]] || { log_info "Skipping — access at: http://localhost:$_display_port" return 0 } # Domain prompt — pre-fill from SITE_DOMAIN when available local _default_domain="" if [[ -n "${SITE_DOMAIN:-}" ]] && [[ "$SITE_DOMAIN" != "example.com" ]]; then _default_domain="${_subdomain}.${SITE_DOMAIN}" log_info "Default: $_default_domain" fi local _domain="" read -r -p " Domain [${_default_domain:-required}]: " _domain _domain="${_domain:-$_default_domain}" [[ -n "$_domain" ]] || { log_warning "No domain entered — skipping Caddy."; return 0; } # Build upstream — remote Caddy uses host IP:port, not container name local _block_upstream="$_upstream" if [[ "$_mode" == "remote" ]]; then _block_upstream="${CADDY_REMOTE_HOST}:${_display_port}" fi local _site_block _site_block="$(cat << CBLOCK # $_name ${_domain} { reverse_proxy ${_block_upstream} header { Strict-Transport-Security "max-age=31536000; includeSubDomains; preload" X-Content-Type-Options "nosniff" X-Frame-Options "SAMEORIGIN" Referrer-Policy "strict-origin-when-cross-origin" } log { output file /var/log/caddy/${_domain}.log format json } ${_extra} } CBLOCK )" if [[ "$_mode" == "local" ]]; then if [[ -f "$_caddyfile" ]]; then local _bk="$_caddy_dir/Caddyfile.backup.$(date +%Y%m%d-%H%M%S)" cp "$_caddyfile" "$_bk" log_info "Backed up Caddyfile to $(basename "$_bk")" else touch "$_caddyfile" fi if grep -q "^${_domain}" "$_caddyfile" 2>/dev/null; then log_warning "$_domain already in Caddyfile" local _ow="" read -r -p " Overwrite? [y/N]: " _ow [[ "${_ow,,}" == "y" ]] || { log_info "Keeping existing entry."; return 0; } sed -i "/^${_domain}/,/^}/d" "$_caddyfile" fi printf '%s\n' "$_site_block" >> "$_caddyfile" log_success "Added $_domain to Caddyfile" docker exec caddy caddy fmt --overwrite /etc/caddy/Caddyfile 2>/dev/null || true if docker exec caddy caddy reload --config /etc/caddy/Caddyfile 2>/dev/null; then log_success "$_name accessible at: https://$_domain" else log_warning "Reload failed — check: docker logs caddy" log_info "Manual reload: docker exec caddy caddy reload --config /etc/caddy/Caddyfile" fi else local _snippet_dir="$DOCKER_DIR/caddy-snippets" local _snippet_file="$_snippet_dir/${_subdomain}.caddy" mkdir -p "$_snippet_dir" printf '%s\n' "$_site_block" > "$_snippet_file" chown "$ACTUAL_USER:$ACTUAL_USER" "$_snippet_file" 2>/dev/null || true log_success "Snippet saved: $_snippet_file" log_info "Copy to Caddy machine:" log_info " scp $_snippet_file caddy-host:~/caddy-snippets/" log_info " rsync -av $_snippet_dir/ caddy-host:~/caddy-snippets/ (all at once)" fi } write_readme() { local _dir="$1"; shift mkdir -p "$_dir" cat > "$_dir/README.md" } backup_if_exists() { local _file="$1" [ -f "$_file" ] || return 0 cp -p "$_file" "${_file}.bak.$(date +%Y%m%d-%H%M%S)" 2>/dev/null } fi # Globals — ACTUAL_USER/ACTUAL_HOME must come before DOCKER_DIR # ($HOME under sudo is /root, not the real user's home) ACTUAL_USER="${ACTUAL_USER:-${SUDO_USER:-$USER}}" ACTUAL_HOME="$(getent passwd "$ACTUAL_USER" 2>/dev/null | cut -d: -f6 || echo "${HOME:-/root}")" DOCKER_DIR="${DOCKER_DIR:-$ACTUAL_HOME/docker}" DRY_RUN="${DRY_RUN:-false}" UNATTENDED="${UNATTENDED:-false}" SITE_TZ="${SITE_TZ:-$(cat /etc/timezone 2>/dev/null || echo UTC)}" SITE_DOMAIN="${SITE_DOMAIN:-example.com}" SITE_CADDY_NET="${SITE_CADDY_NET:-caddy_net}" register_service() { :; } # no-op — no wizard to register into _RUN_STANDALONE=1 fi # ───────────────────────────────────────────────────────────────────────────── register_service gatus utilities "Status & uptime monitoring page (Gatus)" 8086 # ── Caddyfile -> Gatus endpoint sync ──────────────────────────────────────── # Every auto-added endpoint is tagged group: "caddy-sync" — the sync script # only ever adds or removes entries in that exact group, so anything you add # by hand (the default external checks, a custom endpoint, different group # name) is never touched regardless of what the Caddyfile looks like. _gatus_write_sync_script() { local gatus_dir="$1" caddy_file="$2" cat > "$gatus_dir/sync-from-caddy.sh" << 'SYNC_SCRIPT' #!/bin/bash # Auto-generated by services/gatus.sh — do not edit by hand, re-run the # installer to regenerate. Syncs Gatus endpoints with the current # Caddyfile: adds a group: caddy-sync endpoint for every site block found, # removes caddy-sync endpoints for sites no longer there. Never touches # any other endpoint. set -uo pipefail CADDYFILE="$1" GATUS_CONFIG="$2" # Not just `command -v yq` — some distros package a completely different, # incompatible yq (kislyuk's Python jq-wrapper) under the same name; check # it actually identifies as mikefarah's before trusting its syntax. yq --version 2>/dev/null | grep -q mikefarah || { echo "yq unavailable or incompatible — skipping sync"; exit 0; } [ -f "$CADDYFILE" ] || { echo "No Caddyfile at $CADDYFILE — skipping sync"; exit 0; } [ -f "$GATUS_CONFIG" ] || { echo "No Gatus config at $GATUS_CONFIG — skipping sync"; exit 0; } # Site block headers at brace-depth 0, skipping the bare global-options # block (no address before its "{") and parenthesized snippet definitions # like (authelia) — same brace-tracking approach as the Caddy site-block # removal in lib/common.sh (remove_service), for the same reason: a naive # "next blank line" scan is exactly the class of bug that already bit this # repo once on a live Caddy/Samba config. CURRENT_DOMAINS="$(awk ' BEGIN { depth = 0 } { line = $0 opens = gsub(/\{/, "{", line) closes = gsub(/\}/, "}", line) if (depth == 0 && opens > 0) { header = $0 sub(/[[:space:]]*\{.*$/, "", header) gsub(/^[[:space:]]+|[[:space:]]+$/, "", header) if (header != "" && header !~ /^\(/) print header depth += opens - closes next } if (depth > 0) { depth += opens - closes; next } } ' "$CADDYFILE")" EXISTING_SYNCED="$(yq e '.endpoints[] | select(.group == "caddy-sync") | .name' "$GATUS_CONFIG" 2>/dev/null)" ADDED=0 REMOVED=0 # [CONNECTED] == true catches an actual outage (refused/timed-out # connection, DNS failure, TLS failure — [STATUS] reads 0 in all of those, # which is < 400 too, so that condition ALONE would have silently reported # a fully unreachable site as "up"). [STATUS] < 500 accepts anything the # server actually answered with, including 401/403/redirects from an # Authelia-protected site — Gatus's own probe is never logged in, so an # Authelia-gated site correctly returns 401 to it every time, which is the # site working exactly as designed, not an outage. Only Caddy's own # 502/503/504 (backend unreachable) or a connection failure should ever # read as down here. Confirmed live: with the old "[STATUS] < 400" alone, # every Authelia-protected site the user actually logs into showed red # permanently, and a would-be-real outage (STATUS=0) would have shown green. CONDITIONS='["[CONNECTED] == true", "[STATUS] < 500"]' while IFS= read -r domain; do [ -z "$domain" ] && continue # Domains only — a defensive filter, not strictly needed since these # come from our own Caddyfile, but cheap insurance against ever # building a yq expression out of anything unexpected. [[ "$domain" =~ ^[a-zA-Z0-9.-]+$ ]] || continue if grep -qxF "$domain" <<< "$EXISTING_SYNCED"; then # Already synced — refresh its conditions too, not just add-if- # missing, so a template fix like this one reaches every # already-added endpoint on the very next sync instead of leaving # them stuck on whatever conditions they were first created with. yq e -i "(.endpoints[] | select(.group == \"caddy-sync\" and .name == \"${domain}\") | .conditions) = ${CONDITIONS}" "$GATUS_CONFIG" else yq e -i ".endpoints += [{\"name\": \"${domain}\", \"group\": \"caddy-sync\", \"url\": \"https://${domain}\", \"interval\": \"5m\", \"conditions\": ${CONDITIONS}}]" "$GATUS_CONFIG" \ && ADDED=$((ADDED + 1)) fi done <<< "$CURRENT_DOMAINS" while IFS= read -r name; do [ -z "$name" ] && continue if ! grep -qxF "$name" <<< "$CURRENT_DOMAINS"; then yq e -i "del(.endpoints[] | select(.group == \"caddy-sync\" and .name == \"${name}\"))" "$GATUS_CONFIG" \ && REMOVED=$((REMOVED + 1)) fi done <<< "$EXISTING_SYNCED" echo "Gatus sync: added $ADDED, removed $REMOVED endpoint(s) from $(basename "$CADDYFILE")" SYNC_SCRIPT chmod 700 "$gatus_dir/sync-from-caddy.sh" chown "$ACTUAL_USER:$ACTUAL_USER" "$gatus_dir/sync-from-caddy.sh" 2>/dev/null || true } _gatus_setup_caddy_sync() { local gatus_dir="$1" local caddy_file="$DOCKER_DIR/caddy/Caddyfile" [ -f "$caddy_file" ] || return 0 echo "" local ENABLE_SYNC="" prompt_yn "Automatically keep Gatus endpoints in sync with the Caddyfile (syncs now, then every 15 minutes)? (y/n):" "y" ENABLE_SYNC [[ "$ENABLE_SYNC" =~ ^[Yy]$ ]] || return 0 declare -F ensure_yq >/dev/null 2>&1 && ensure_yq command -v yq >/dev/null 2>&1 || { log_warning "yq unavailable — skipping Caddy sync."; return 0; } _gatus_write_sync_script "$gatus_dir" "$caddy_file" "$gatus_dir/sync-from-caddy.sh" "$caddy_file" "$gatus_dir/gatus_config/config.yaml" if command -v systemctl >/dev/null 2>&1; then cat > /etc/systemd/system/gatus-caddy-sync.service << UNIT [Unit] Description=Sync Gatus endpoints from Caddyfile [Service] Type=oneshot ExecStart=${gatus_dir}/sync-from-caddy.sh ${caddy_file} ${gatus_dir}/gatus_config/config.yaml UNIT cat > /etc/systemd/system/gatus-caddy-sync.timer << 'UNIT' [Unit] Description=Periodic Gatus/Caddyfile sync [Timer] OnBootSec=5min OnUnitActiveSec=15min [Install] WantedBy=timers.target UNIT systemctl daemon-reload if systemctl enable --now gatus-caddy-sync.timer >/dev/null 2>&1; then log_success "Sync scheduled every 15 minutes (systemd timer: gatus-caddy-sync)" else log_warning "Couldn't enable the sync timer — re-run $gatus_dir/sync-from-caddy.sh manually after Caddyfile changes." fi else log_warning "No systemd — synced once, but won't auto-repeat. Re-run $gatus_dir/sync-from-caddy.sh manually after Caddyfile changes." fi } install_gatus() { require_docker || return 1 log_info "Installing Gatus..." local GATUS_DIR="$DOCKER_DIR/gatus" local WEB_PORT="8086" if [ "$DRY_RUN" = true ]; then echo "[DRY-RUN] Would create $GATUS_DIR (gatus_config/, gatus_data/)" echo "[DRY-RUN] Would deploy twinproduction/gatus:latest" echo "[DRY-RUN] Port 8086 published (auto-scanned for a free host port)," echo "[DRY-RUN] config at gatus_config/config.yaml" echo "[DRY-RUN] Would offer to auto-sync endpoints from the Caddyfile (adds/removes group: caddy-sync entries, every 15min via a systemd timer)" return 0 fi # Scan for a free host port — a plain install shouldn't silently claim a # port another already-running service holds. See CLAUDE.md's "Port # collision avoidance" section. find_free_port WEB_PORT "$WEB_PORT" mkdir -p "$GATUS_DIR/gatus_config" "$GATUS_DIR/gatus_data" ensure_docker_dir_ownership "$GATUS_DIR" cd "$GATUS_DIR" || return 1 local TZ_VAL="${SITE_TZ:-$(cat /etc/timezone 2>/dev/null || echo UTC)}" # Mirrors configure_caddy_for_service's own mode resolution (lib/common.sh): # explicit CADDY_MODE from the site config wins, then a local ~/docker/caddy, # then the legacy CADDY_REMOTE_HOST var. Only "local" joins caddy_net — a # remote Caddy box can't resolve container names on this host's bridge # network anyway; it reaches this service via the host's published port. local _CADDY_MODE="${CADDY_MODE:-none}" [ "$_CADDY_MODE" = "none" ] && [ -d "$DOCKER_DIR/caddy" ] && _CADDY_MODE="local" [ "$_CADDY_MODE" = "none" ] && [ -n "${CADDY_REMOTE_HOST:-}" ] && _CADDY_MODE="remote" local _CADDY_NET_BLOCK="" local _CADDY_NET_SECTION="" if [ "$_CADDY_MODE" = "local" ]; then _CADDY_NET_BLOCK=" networks: - caddy_net " _CADDY_NET_SECTION=" networks: caddy_net: external: true name: ${SITE_CADDY_NET:-caddy_net} " fi backup_if_exists docker-compose.yml cat > docker-compose.yml << GATUS_COMPOSE name: gatus services: gatus: image: twinproduction/gatus:latest container_name: gatus hostname: gatus restart: unless-stopped env_file: .env ports: - "${WEB_PORT}:8080" volumes: - ./gatus_config:/config - ./gatus_data:/data ${_CADDY_NET_BLOCK}${_CADDY_NET_SECTION} GATUS_COMPOSE backup_if_exists .env cat > .env << GATUS_ENV TZ=$TZ_VAL CADDY_NET=$SITE_CADDY_NET GATUS_ENV # Write a sample config if none exists if [ ! -f gatus_config/config.yaml ]; then cat > gatus_config/config.yaml << 'GATUS_CFG' # Gatus configuration — docs: https://github.com/TwiN/gatus # # Add or remove endpoints below. Config is hot-reloaded on changes. # Alert types: ntfy, slack, discord, email, telegram, and more. storage: type: sqlite path: /data/gatus.db ui: title: "Status" header: "Services" # ── Endpoints ───────────────────────────────────────────────────────────────── endpoints: - name: Google DNS group: external url: "8.8.8.8" dns: query-name: "google.com" query-type: "A" interval: 5m conditions: - "[DNS_RCODE] == NOERROR" - name: Example HTTPS group: external url: "https://example.com" interval: 5m conditions: - "[STATUS] == 200" - "[RESPONSE_TIME] < 3000" - "[CERTIFICATE_EXPIRATION] > 48h" # ── Add your services below ──────────────────────────────────────────────── # - name: Mealie # group: homelab # url: "http://mealie:9000/api/app/about" # interval: 1m # conditions: # - "[STATUS] == 200" # - "[RESPONSE_TIME] < 500" # # - name: Portainer # group: homelab # url: "https://portainer:9443" # interval: 1m # conditions: # - "[STATUS] == 200" # client: # insecure: true GATUS_CFG fi chown -R "$ACTUAL_USER:$ACTUAL_USER" "$GATUS_DIR" log_success "Gatus configured at $GATUS_DIR" configure_caddy_for_service "Gatus" "gatus:8080" "status" write_readme "$GATUS_DIR" << MD # Gatus — status & uptime monitoring Clean, self-hosted status page. Polls HTTP, TCP, DNS, and ICMP endpoints. ## Access - URL: http://localhost:${WEB_PORT} ## Configuration Edit \`gatus_config/config.yaml\` — changes are **hot-reloaded** without restarting. Key concepts: - \`endpoints:\` — what to check (HTTP, TCP, DNS, ICMP) - \`interval:\` — how often (e.g. 1m, 5m) - \`conditions:\` — pass/fail rules ([STATUS], [RESPONSE_TIME], etc.) - \`alerts:\` — notify via ntfy, Slack, Discord, email, etc. Full docs: https://github.com/TwiN/gatus ## Caddyfile sync If you enabled it during install, \`sync-from-caddy.sh\` runs every 15 minutes (systemd timer: \`gatus-caddy-sync\`) and keeps one endpoint per Caddy site block in sync automatically — added when a new site appears, removed when one goes away. Every auto-added endpoint is tagged \`group: caddy-sync\`; the sync only ever touches entries in that group, so anything you add or edit by hand (a different group, the default external checks) is left alone no matter what. Run it by hand any time instead of waiting for the timer: \`\`\`bash $GATUS_DIR/sync-from-caddy.sh $DOCKER_DIR/caddy/Caddyfile $GATUS_DIR/gatus_config/config.yaml \`\`\` Check/manage the timer: \`\`\`bash systemctl status gatus-caddy-sync.timer systemctl list-timers gatus-caddy-sync.timer sudo systemctl disable --now gatus-caddy-sync.timer # turn it off \`\`\` ## Manage \`\`\`bash cd $GATUS_DIR docker compose up -d # start docker compose down # stop docker compose logs -f # logs (check config errors here) docker compose pull && docker compose up -d # update \`\`\` MD local START_GATUS="" prompt_yn "Start Gatus now? (y/n):" "y" START_GATUS if [ "$START_GATUS" = "y" ] || [ "$START_GATUS" = "Y" ]; then docker compose up -d \ && log_success "Gatus started" \ || log_warning "Failed to start — check: docker compose logs" fi _gatus_setup_caddy_sync "$GATUS_DIR" echo " Access at: http://localhost:${WEB_PORT}" echo " Config: $GATUS_DIR/gatus_config/config.yaml (hot-reloaded)" echo "" } # Run immediately when executed directly (deferred until after function definition) [[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_gatus