personal_infra/ansible/infra/nodito/40_cpu_temp_alerts.yml

- name: Deploy Nodito CPU Temperature Monitoring
  hosts: nodito
  become: yes
  vars_files:
  - ../../infra_vars.yml
  - ./nodito_vars.yml
  - ./nodito_secrets.yml

  tasks:
    - name: Validate Uptime Kuma URL is provided
      assert:
        that:
          - nodito_uptime_kuma_cpu_temp_push_url != ""
        fail_msg: "uptime_kuma_url must be set in nodito_secrets.yml"

    - name: Install required packages for temperature monitoring
      package:
        name:
          - lm-sensors
          - curl
          - jq
          - bc
        state: present

    - name: Create monitoring script directory
      file:
        path: "{{ monitoring_script_dir }}"
        state: directory
        owner: root
        group: root
        mode: '0755'

    - name: Create CPU temperature monitoring script
      copy:
        dest: "{{ monitoring_script_path }}"
        content: |
          #!/bin/bash
          
          # CPU Temperature Monitoring Script for Nodito
          # Monitors CPU temperature and sends alerts to Uptime Kuma
          
          LOG_FILE="{{ log_file }}"
          TEMP_THRESHOLD="{{ temp_threshold_celsius }}"
          UPTIME_KUMA_URL="{{ nodito_uptime_kuma_cpu_temp_push_url }}"
          
          # Function to log messages
          log_message() {
              echo "$(date '+%Y-%m-%d %H:%M:%S') - $1" >> "$LOG_FILE"
          }
          
          # Function to get CPU temperature
          get_cpu_temp() {
              # Try different methods to get CPU temperature
              local temp=""
              
              # Method 1: sensors command (most common)
              if command -v sensors >/dev/null 2>&1; then
                  temp=$(sensors 2>/dev/null | grep -E "Core 0|Package id 0|Tdie|Tctl" | head -1 | grep -oE '[0-9]+\.[0-9]+°C' | grep -oE '[0-9]+\.[0-9]+')
              fi
              
              # Method 2: thermal zone (fallback)
              if [ -z "$temp" ] && [ -f /sys/class/thermal/thermal_zone0/temp ]; then
                  temp=$(cat /sys/class/thermal/thermal_zone0/temp)
                  temp=$(echo "scale=1; $temp/1000" | bc -l 2>/dev/null || echo "$temp")
              fi
              
              # Method 3: acpi (fallback)
              if [ -z "$temp" ] && command -v acpi >/dev/null 2>&1; then
                  temp=$(acpi -t 2>/dev/null | grep -oE '[0-9]+\.[0-9]+' | head -1)
              fi
              
              echo "$temp"
          }
          
          # Function to send alert to Uptime Kuma
          send_uptime_kuma_alert() {
              local temp="$1"
              local message="CPU Temperature Alert: ${temp}°C (Threshold: ${TEMP_THRESHOLD}°C)"
              
              log_message "ALERT: $message"
              
              # Send push notification to Uptime Kuma
              encoded_message=$(printf '%s\n' "$message" | sed 's/ /%20/g; s/°/%C2%B0/g; s/(/%28/g; s/)/%29/g; s/:/%3A/g')
              curl "$UPTIME_KUMA_URL?status=up&msg=$encoded_message"
              
              if [ $? -eq 0 ]; then
                  log_message "Alert sent successfully to Uptime Kuma"
              else
                  log_message "ERROR: Failed to send alert to Uptime Kuma"
              fi
          }
          
          # Main monitoring logic
          main() {
              log_message "Starting CPU temperature check"
              
              # Get current CPU temperature
              current_temp=$(get_cpu_temp)
              
              if [ -z "$current_temp" ]; then
                  log_message "ERROR: Could not read CPU temperature"
                  exit 1
              fi
              
              log_message "Current CPU temperature: ${current_temp}°C"
              
              # Check if temperature exceeds threshold
              if (( $(echo "$current_temp > $TEMP_THRESHOLD" | bc -l) )); then
                  log_message "WARNING: CPU temperature ${current_temp}°C exceeds threshold ${TEMP_THRESHOLD}°C"
                  send_uptime_kuma_alert "$current_temp"
              else
                  log_message "CPU temperature is within normal range"
              fi
          }
          
          # Run main function
          main
        owner: root
        group: root
        mode: '0755'

    - name: Create systemd service for CPU temperature monitoring
      copy:
        dest: "/etc/systemd/system/{{ systemd_service_name }}.service"
        content: |
          [Unit]
          Description=Nodito CPU Temperature Monitor
          After=network.target
          
          [Service]
          Type=oneshot
          ExecStart={{ monitoring_script_path }}
          User=root
          StandardOutput=journal
          StandardError=journal
          
          [Install]
          WantedBy=multi-user.target
        owner: root
        group: root
        mode: '0644'

    - name: Create systemd timer for CPU temperature monitoring
      copy:
        dest: "/etc/systemd/system/{{ systemd_service_name }}.timer"
        content: |
          [Unit]
          Description=Run Nodito CPU Temperature Monitor every {{ temp_check_interval_minutes }} minute(s)
          Requires={{ systemd_service_name }}.service
          
          [Timer]
          OnBootSec={{ temp_check_interval_minutes }}min
          OnUnitActiveSec={{ temp_check_interval_minutes }}min
          Persistent=true
          
          [Install]
          WantedBy=timers.target
        owner: root
        group: root
        mode: '0644'

    - name: Reload systemd daemon
      systemd:
        daemon_reload: yes

    - name: Enable and start CPU temperature monitoring timer
      systemd:
        name: "{{ systemd_service_name }}.timer"
        enabled: yes
        state: started

    - name: Test CPU temperature monitoring script
      command: "{{ monitoring_script_path }}"
      register: script_test
      changed_when: false

    - name: Verify script execution
      assert:
        that:
          - script_test.rc == 0
        fail_msg: "CPU temperature monitoring script failed to execute properly"

    - name: Check if sensors are available
      command: sensors
      register: sensors_check
      changed_when: false
      failed_when: false

    - name: Display sensor information
      debug:
        msg: "Sensor information: {{ sensors_check.stdout_lines if sensors_check.rc == 0 else 'Sensors not available - using fallback methods' }}"

    - name: Show monitoring configuration
      debug:
        msg:
          - "CPU Temperature Monitoring configured successfully"
          - "Temperature threshold: {{ temp_threshold_celsius }}°C"
          - "Check interval: {{ temp_check_interval_minutes }} minute(s)"
          - "Uptime Kuma URL: {{ nodito_uptime_kuma_cpu_temp_push_url }}"
          - "Monitoring script: {{ monitoring_script_path }}"
          - "Log file: {{ log_file }}"
          - "Service: {{ systemd_service_name }}.service"
          - "Timer: {{ systemd_service_name }}.timer"