deploy: Dockerfile, Compose pro Rolle, LiteLLM, Prometheus/Alertmanager, Canary-Prober, n8n-Workflows

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 00:51:31 +02:00
parent 4cbe313c62
commit cb5a413169
28 changed files with 1731 additions and 9 deletions
@@ -0,0 +1,104 @@
+# Rolle "infra" (LXC/VM auf einem i7-Node): Router, LiteLLM, Postgres, Monitoring.
+# Start: cp .env.example .env && docker compose up -d
+name: knaster-infra
+
+x-restart: &restart
+  restart: unless-stopped
+  labels: {autoheal: "true"}
+
+services:
+  router:
+    <<: *restart
+    build:
+      context: ../../..
+      dockerfile: deploy/docker/router.Dockerfile
+    image: knaster/router:${KNASTER_VERSION:-dev}
+    env_file: .env
+    environment:
+      KNASTER_DB_URL: postgresql+psycopg://knaster:${POSTGRES_PASSWORD:?POSTGRES_PASSWORD fehlt}@postgres:5432/knaster
+      KNASTER_SITE_DIR: /app/sites/${KNASTER_SITE:-knaster}
+      LITELLM_BASE_URL: http://litellm:4000
+    ports: ["8080:8080"]
+    depends_on:
+      postgres: {condition: service_healthy}
+      litellm: {condition: service_started}
+
+  litellm:
+    <<: *restart
+    image: ghcr.io/berriai/litellm:${LITELLM_TAG:-main-stable}   # vor Deployment auf feste Version pinnen
+    command: ["--config", "/app/config.yaml", "--port", "4000"]
+    env_file: .env
+    volumes:
+      - ../../litellm/config.yaml:/app/config.yaml:ro
+    ports: ["4000:4000"]
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:4000/health/liveliness', timeout=4)"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+
+  postgres:
+    <<: *restart
+    image: pgvector/pgvector:pg16
+    environment:
+      POSTGRES_USER: knaster
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?POSTGRES_PASSWORD fehlt}
+      POSTGRES_DB: knaster
+    volumes:
+      - postgres:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U knaster -d knaster"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  prometheus:
+    <<: *restart
+    image: prom/prometheus:v2.53.0
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.retention.time=15d
+      - --web.enable-lifecycle
+    volumes:
+      - ../../prometheus:/etc/prometheus:ro
+      - prometheus:/prometheus
+    ports: ["9090:9090"]
+
+  alertmanager:
+    <<: *restart
+    image: prom/alertmanager:v0.27.0
+    command: ["--config.file=/etc/alertmanager/alertmanager.yml"]
+    volumes:
+      - ../../alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
+      - ./secrets/router_token:/etc/alertmanager/router_token:ro
+    ports: ["9093:9093"]
+
+  grafana:
+    <<: *restart
+    image: grafana/grafana:11.1.0
+    profiles: ["dashboards"]
+    volumes:
+      - grafana:/var/lib/grafana
+    ports: ["3000:3000"]
+
+  pve-exporter:
+    <<: *restart
+    image: prompve/prometheus-pve-exporter:${PVE_EXPORTER_TAG:-latest}   # vor Deployment pinnen
+    profiles: ["proxmox"]
+    volumes:
+      - ./secrets/pve.yml:/etc/prometheus/pve.yml:ro
+    ports: ["9221:9221"]
+
+  autoheal:
+    restart: unless-stopped
+    image: willfarrell/autoheal:1.2.0
+    environment:
+      AUTOHEAL_CONTAINER_LABEL: autoheal
+      AUTOHEAL_INTERVAL: "15"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+
+volumes:
+  postgres: {}
+  prometheus: {}
+  grafana: {}