Initial Ansible automation for hobbs.farm infrastructure

Complete IaC covering:
- 14 roles: common, docker, traefik, vaultwarden, monitoring, media, matrix,
  home_assistant, frigate, adguard, gitea, semaphore, openclaw, security, backup
- Inventory for all hosts (Peggy, Bart, Yoda, NAS, Firewalla)
- Stack playbooks: core-infrastructure, monitoring, media, communication,
  automation, smarthome, security-hardening
- Maintenance playbooks: update-containers, backup, health-check
- Production Docker Compose templates with Traefik labels
- Security hardening (sysctl, auditd, UFW, fail2ban)
- Automated backups with retention policy

roles/monitoring/defaults/main.yml

@@ -0,0 +1,18 @@
+---
+monitoring_compose_dir: "{{ docker_compose_base }}/monitoring"
+prometheus_data_dir: /data/prometheus
+grafana_data_dir: /data/grafana
+alertmanager_data_dir: /data/alertmanager
+
+prometheus_image: "prom/prometheus:latest"
+grafana_image: "grafana/grafana:latest"
+alertmanager_image: "prom/alertmanager:latest"
+node_exporter_image: "prom/node-exporter:latest"
+cadvisor_image: "gcr.io/cadvisor/cadvisor:latest"
+
+prometheus_retention: 30d
+prometheus_scrape_interval: 15s
+grafana_admin_password: "{{ vault_grafana_admin_password }}"
+grafana_host: "grafana.{{ domain }}"
+prometheus_host: "prometheus.{{ domain }}"
+alertmanager_host: "alertmanager.{{ domain }}"

roles/monitoring/handlers/main.yml

@@ -0,0 +1,6 @@
+---
+- name: Restart monitoring stack
+  community.docker.docker_compose_v2:
+    project_src: "{{ monitoring_compose_dir }}"
+    state: present
+    recreate: always

roles/monitoring/tasks/main.yml

@@ -0,0 +1,61 @@
+---
+- name: Create monitoring directories
+  ansible.builtin.file:
+    path: "{{ item }}"
+    state: directory
+    owner: glyptic
+    group: docker
+    mode: "0755"
+  loop:
+    - "{{ monitoring_compose_dir }}"
+    - "{{ prometheus_data_dir }}"
+    - "{{ prometheus_data_dir }}/config"
+    - "{{ grafana_data_dir }}"
+    - "{{ alertmanager_data_dir }}"
+    - "{{ alertmanager_data_dir }}/config"
+  tags: [monitoring]
+
+- name: Set Grafana data directory ownership
+  ansible.builtin.file:
+    path: "{{ grafana_data_dir }}"
+    state: directory
+    owner: "472"
+    group: "472"
+    mode: "0755"
+  tags: [monitoring, grafana]
+
+- name: Deploy Prometheus configuration
+  ansible.builtin.template:
+    src: prometheus.yml.j2
+    dest: "{{ prometheus_data_dir }}/config/prometheus.yml"
+    owner: glyptic
+    group: docker
+    mode: "0644"
+  notify: Restart monitoring stack
+  tags: [monitoring, prometheus]
+
+- name: Deploy Alertmanager configuration
+  ansible.builtin.template:
+    src: alertmanager.yml.j2
+    dest: "{{ alertmanager_data_dir }}/config/alertmanager.yml"
+    owner: glyptic
+    group: docker
+    mode: "0644"
+  notify: Restart monitoring stack
+  tags: [monitoring, alertmanager]
+
+- name: Deploy monitoring compose file
+  ansible.builtin.template:
+    src: docker-compose.yml.j2
+    dest: "{{ monitoring_compose_dir }}/docker-compose.yml"
+    owner: glyptic
+    group: docker
+    mode: "0644"
+  notify: Restart monitoring stack
+  tags: [monitoring]
+
+- name: Start monitoring stack
+  community.docker.docker_compose_v2:
+    project_src: "{{ monitoring_compose_dir }}"
+    state: present
+  tags: [monitoring]

roles/monitoring/templates/alertmanager.yml.j2

@@ -0,0 +1,29 @@
+global:
+  resolve_timeout: 5m
+{% if alertmanager_smtp_host is defined and alertmanager_smtp_host %}
+  smtp_smarthost: "{{ alertmanager_smtp_host }}"
+  smtp_from: "{{ alertmanager_smtp_from }}"
+{% endif %}
+
+route:
+  group_by: ["alertname", "instance"]
+  group_wait: 30s
+  group_interval: 5m
+  repeat_interval: 4h
+  receiver: default
+
+receivers:
+  - name: default
+{% if alertmanager_slack_webhook is defined and alertmanager_slack_webhook %}
+    slack_configs:
+      - api_url: "{{ alertmanager_slack_webhook }}"
+        channel: "#alerts"
+        send_resolved: true
+{% endif %}
+
+inhibit_rules:
+  - source_match:
+      severity: critical
+    target_match:
+      severity: warning
+    equal: ["alertname", "instance"]

roles/monitoring/templates/docker-compose.yml.j2

@@ -0,0 +1,86 @@
+services:
+  prometheus:
+    image: {{ prometheus_image }}
+    container_name: prometheus
+    restart: unless-stopped
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.path=/prometheus
+      - --storage.tsdb.retention.time={{ prometheus_retention }}
+      - --web.enable-lifecycle
+    volumes:
+      - {{ prometheus_data_dir }}/config/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - {{ prometheus_data_dir }}/data:/prometheus
+    labels:
+      traefik.enable: "true"
+      traefik.http.routers.prometheus.rule: "Host(`{{ prometheus_host }}`)"
+      traefik.http.routers.prometheus.entrypoints: websecure
+      traefik.http.routers.prometheus.tls.certresolver: cloudflare
+      traefik.http.services.prometheus.loadbalancer.server.port: "9090"
+    networks:
+      - {{ docker_network_name }}
+
+  grafana:
+    image: {{ grafana_image }}
+    container_name: grafana
+    restart: unless-stopped
+    environment:
+      GF_SECURITY_ADMIN_PASSWORD: {{ grafana_admin_password }}
+      GF_SERVER_ROOT_URL: "https://{{ grafana_host }}"
+      GF_SERVER_DOMAIN: "{{ grafana_host }}"
+    volumes:
+      - {{ grafana_data_dir }}:/var/lib/grafana
+    labels:
+      traefik.enable: "true"
+      traefik.http.routers.grafana.rule: "Host(`{{ grafana_host }}`)"
+      traefik.http.routers.grafana.entrypoints: websecure
+      traefik.http.routers.grafana.tls.certresolver: cloudflare
+      traefik.http.services.grafana.loadbalancer.server.port: "3000"
+    networks:
+      - {{ docker_network_name }}
+
+  alertmanager:
+    image: {{ alertmanager_image }}
+    container_name: alertmanager
+    restart: unless-stopped
+    command:
+      - --config.file=/etc/alertmanager/alertmanager.yml
+    volumes:
+      - {{ alertmanager_data_dir }}/config/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
+    labels:
+      traefik.enable: "true"
+      traefik.http.routers.alertmanager.rule: "Host(`{{ alertmanager_host }}`)"
+      traefik.http.routers.alertmanager.entrypoints: websecure
+      traefik.http.routers.alertmanager.tls.certresolver: cloudflare
+      traefik.http.services.alertmanager.loadbalancer.server.port: "9093"
+    networks:
+      - {{ docker_network_name }}
+
+  node-exporter:
+    image: {{ node_exporter_image }}
+    container_name: node-exporter
+    restart: unless-stopped
+    command:
+      - --path.rootfs=/host
+    volumes:
+      - /:/host:ro,rslave
+    pid: host
+    networks:
+      - {{ docker_network_name }}
+
+  cadvisor:
+    image: {{ cadvisor_image }}
+    container_name: cadvisor
+    restart: unless-stopped
+    privileged: true
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:ro
+      - /sys:/sys:ro
+      - /var/lib/docker:/var/lib/docker:ro
+    networks:
+      - {{ docker_network_name }}
+
+networks:
+  {{ docker_network_name }}:
+    external: true

roles/monitoring/templates/prometheus.yml.j2

@@ -0,0 +1,37 @@
+global:
+  scrape_interval: {{ prometheus_scrape_interval }}
+  evaluation_interval: {{ prometheus_scrape_interval }}
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+            - alertmanager:9093
+
+scrape_configs:
+  - job_name: prometheus
+    static_configs:
+      - targets: ["localhost:9090"]
+
+  - job_name: node-exporter
+    static_configs:
+      - targets:
+          - node-exporter:9100
+        labels:
+          instance: peggy
+      - targets:
+          - 192.168.86.181:9100
+        labels:
+          instance: bart
+
+  - job_name: cadvisor
+    static_configs:
+      - targets: ["cadvisor:8080"]
+
+  - job_name: traefik
+    static_configs:
+      - targets: ["traefik:8080"]
+
+  - job_name: adguard
+    static_configs:
+      - targets: ["adguard-exporter:9617"]