Add self-hosted Healthchecks stack for internal job monitoring (hybrid)

Self-hosted Healthchecks (ops/healthchecks/) as the hub for internal cron/job heartbeats. The three host-down/backup watchdogs (Borg pre-hook, baerchen nearline pull, monitoring watchdog #8) deliberately stay on healthchecks.io cloud, since an on-host watcher cannot report a host outage. - frontend_net + dedicated PostgreSQL 18 in healthchecks_internal - native Healthchecks auth; ping/API exempt from Authelia (n8n/Komodo pattern) - registered as middleware_exempt in ops/policy-checks/exceptions.json - docs: DECISIONS, ARCHITECTURE (3.1/4.2/7.6/10), SERVICE_CATALOG, SECRETS_MAP, MASTER_TODO, README index docker compose config validated (exit 0). Not yet deployed: host secret file, appdata dir, Komodo stack + ENV and Gitea webhook remain operator steps. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 20:09:56 +02:00
parent ee0d450a27
commit cbfbb8ca4f
9 changed files with 291 additions and 0 deletions
@@ -0,0 +1,124 @@
+name: healthchecks
+
+# Self-gehostetes Healthchecks (Dead-Man's-Switch / Cron-Heartbeat-Monitor).
+#
+# SCOPE (bewusst): Hub fuer die vielen INTERNEN Jobs/Scripte, die auf einem
+# laufenden Host melden sollen "lief Job X heute?" (posture-check,
+# restore-tests, pre-backup-dumps, gitea-bundle-mirror, ...).
+#
+# NICHT hier: die host-down-/backup-still-Waechter (Borg-Pre-Hook,
+# baerchen-Nearline-Pull, Monitoring-Watchdog #8) bleiben bewusst EXTERN auf
+# healthchecks.io-Cloud. Ein Waechter auf demselben Host kann einen
+# Host-Ausfall nicht melden (er ist dann selbst tot). Siehe ops/healthchecks/README.md.
+
+services:
+  healthchecks:
+    image: healthchecks/healthchecks:v4.2@sha256:6b5f593d40994345053f05f86decfa9e17ab1e4422df2ae58abd032a7b14d8f6
+    container_name: healthchecks
+    restart: unless-stopped
+
+    # ntfy-Integration nutzt die oeffentliche Traefik-URL; Container-DNS loest
+    # ntfy.kaleschke.info sonst nicht (gleiches Muster wie mealie/komodo).
+    extra_hosts:
+      - "ntfy.kaleschke.info:192.168.178.58"
+
+    environment:
+      TZ: Europe/Berlin
+      DEBUG: "False"
+      SITE_ROOT: https://hc.kaleschke.info
+      SITE_NAME: KalliLab Healthchecks
+      ALLOWED_HOSTS: hc.kaleschke.info,localhost
+      REGISTRATION_OPEN: "False"
+
+      DB: postgres
+      DB_HOST: healthchecks-postgres
+      DB_PORT: "5432"
+      DB_NAME: healthchecks
+      DB_USER: healthchecks
+      DB_PASSWORD: ${HEALTHCHECKS_DB_PASSWORD}
+
+      SECRET_KEY: ${HEALTHCHECKS_SECRET_KEY}
+
+      # Erst-Admin wird beim Start angelegt/aktualisiert. Werte nur als
+      # Komodo-Stack-ENV, niemals im Repo. SMTP ist bewusst nicht konfiguriert
+      # (Login via Superuser-Passwort, Benachrichtigung via ntfy-Integration).
+      SUPERUSER_EMAIL: ${HEALTHCHECKS_SUPERUSER_EMAIL}
+      SUPERUSER_PASSWORD: ${HEALTHCHECKS_SUPERUSER_PASSWORD}
+
+    networks:
+      - frontend_net
+      - healthchecks_internal
+
+    depends_on:
+      healthchecks-postgres:
+        condition: service_healthy
+
+    healthcheck:
+      test: ["CMD-SHELL", "python -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:8000/', timeout=5).status==200 else 1)\""]
+      interval: 60s
+      timeout: 10s
+      retries: 5
+      start_period: 60s
+
+    security_opt:
+      - no-new-privileges:true
+
+    labels:
+      # Traefik mit nativer Healthchecks-Auth, bewusst OHNE pauschale
+      # authelia@file: die Ping-Endpunkte (/ping/*) und die API muessen ohne
+      # ForwardAuth erreichbar sein, sonst koennen Cron-Jobs nicht melden
+      # (gleiche Ausnahme-Logik wie n8n/Komodo). Dashboard ist durch den
+      # Healthchecks-eigenen Login geschuetzt.
+      - traefik.enable=true
+      - traefik.docker.network=frontend_net
+      - traefik.http.routers.healthchecks.rule=Host(`hc.kaleschke.info`)
+      - traefik.http.routers.healthchecks.entrypoints=websecure
+      - traefik.http.routers.healthchecks.tls=true
+      - traefik.http.routers.healthchecks.tls.certresolver=le
+      - traefik.http.routers.healthchecks.middlewares=secure-headers@file
+      - traefik.http.services.healthchecks.loadbalancer.server.port=8000
+
+  healthchecks-postgres:
+    image: postgres:18.4@sha256:29ee7bb30d804447dc9a91fd0d74322ae1dc3a4072cc6346f70a5ed6e783b565
+    container_name: healthchecks-postgres
+    restart: unless-stopped
+
+    environment:
+      TZ: Europe/Berlin
+      POSTGRES_USER: healthchecks
+      POSTGRES_DB: healthchecks
+      POSTGRES_PASSWORD_FILE: /run/secrets/healthchecks_postgres_password
+      PGDATA: /var/lib/postgresql/18/docker
+
+    volumes:
+      - /mnt/user/appdata/healthchecks/postgres18:/var/lib/postgresql
+
+    networks:
+      - healthchecks_internal
+
+    secrets:
+      - healthchecks_postgres_password
+
+    expose:
+      - "5432"
+
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U \"$${POSTGRES_USER}\" -d \"$${POSTGRES_DB}\""]
+      interval: 10s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
+    security_opt:
+      - no-new-privileges:true
+
+networks:
+  frontend_net:
+    external: true
+  healthchecks_internal:
+    driver: bridge
+    internal: true
+
+secrets:
+  healthchecks_postgres_password:
+    file: /mnt/user/appdata/secrets/healthchecks_postgres_password.txt