Dockerised and prepared with .env

.env.example

@@ -0,0 +1,32 @@
+# Thinkcentre Monitor Configuration
+# Copy this file to .env and fill in your actual values
+
+# Target URL to monitor for health checks
+# This is the service URL that will be checked every CHECK_INTERVAL seconds
+TARGET_URL=http://kubernetes-service:8080
+
+# Home Assistant configuration
+# HA_URL: Base URL of your Home Assistant instance
+# Example: http://homeassistant:8123 or http://192.168.1.100:8123
+HA_URL=http://homeassistant:8123
+
+# HA_TOKEN: Long-lived access token from Home Assistant
+# To generate: Home Assistant Settings → Developer Tools → Long-Lived Access Tokens
+# REQUIRED - the script will exit if this is not set
+HA_TOKEN=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiI5MGUzZjBmZTYwMjc0NWU0YTAwOTdiOTk2MjY1MzU2YyIsImlhdCI6MTczMzQwMjEwMiwiZXhwIjoyMDQ4NzYyMTAyfQ.example_token_replace_with_yours
+
+# HA_ENTITY: Home Assistant entity ID for the power switch
+# This is the switch entity that will be toggled to power-cycle the machine
+# Example: switch.thinkcentre_power or switch.machine_reboot_relay
+HA_ENTITY=switch.thinkcentre_power
+
+# Grace period in seconds
+# When a 502 error is detected, the system waits this long for recovery
+# (useful for deployment scenarios where services may temporarily be unavailable)
+# Default: 300 (5 minutes)
+GRACE_PERIOD=300
+
+# Health check interval in seconds
+# How frequently to check the target URL
+# Default: 30 seconds
+CHECK_INTERVAL=30

Dockerfile

@@ -0,0 +1,22 @@
+FROM alpine:latest
+
+# Install required dependencies
+RUN apk add --no-cache \
+    bash \
+    curl \
+    ca-certificates
+
+# Create application directory
+WORKDIR /app
+
+# Copy monitoring script
+COPY thinkcenter_monitor.sh /app/thinkcenter_monitor.sh
+
+# Create log directory
+RUN mkdir -p /var/log
+
+# Make script executable
+RUN chmod +x /app/thinkcenter_monitor.sh
+
+# Set the entrypoint
+CMD ["/app/thinkcenter_monitor.sh"]

README.md

@@ -1,3 +1,242 @@
-# Thinkcentre-watchdog
+# Thinkcentre Watchdog
 
-A watchdog daemon for my thinkcentre machines which tend to hang.
+A Docker-based monitoring solution for detecting and auto-rebooting hung Kubernetes machines via Home Assistant integration.
+
+## Overview
+
+This watchdog monitors a target service URL for 502 Bad Gateway errors (indicating a hung machine). When a service fails:
+
+1. A 5-minute grace period begins (allowing for deployment recoveries)
+2. If the service recovers within 5 minutes, the error is cleared (normal deployment scenario)
+3. If still failing after 5 minutes, an automatic power-cycle is triggered via Home Assistant
+4. The machine powers off for 10 seconds, then powers back on
+
+All activity is logged with timestamps for monitoring and troubleshooting.
+
+## Prerequisites
+
+- Docker and Docker Compose installed
+- Home Assistant instance running with network access
+- A power switch entity configured in Home Assistant
+- Long-lived access token from Home Assistant
+
+## Installation
+
+### 1. Download/Organize Files
+
+Clone or download this repository to your machine:
+
+```bash
+git clone <repository-url>
+cd Thinkcentre-watchdog
+```
+
+The directory should contain:
+- `Dockerfile` - Container definition
+- `thinkcenter_monitor.sh` - Monitoring script
+- `docker-compose.yml` - Docker Compose configuration
+- `.env.example` - Environment variable template
+- `README.md` - This file
+
+### 2. Create Configuration File
+
+Copy the example environment file and edit it with your actual values:
+
+```bash
+cp .env.example .env
+```
+
+Edit `.env` and configure:
+
+```bash
+# Your target service URL
+TARGET_URL=http://your-kubernetes-service:8080
+
+# Home Assistant configuration
+HA_URL=http://homeassistant:8123
+HA_TOKEN=your_long_lived_access_token_here
+HA_ENTITY=switch.your_power_switch_entity
+
+# Optional: Adjust timing if needed
+GRACE_PERIOD=300      # 5 minutes
+CHECK_INTERVAL=30     # Check every 30 seconds
+```
+
+### 3. Generate Home Assistant Token
+
+1. Open Home Assistant web interface
+2. Go to **Settings** → **Developer Tools** → **Long-Lived Access Tokens**
+3. Click **Create Token**
+4. Name it (e.g., "Thinkcentre Watchdog")
+5. Copy the token and paste it in your `.env` file as `HA_TOKEN`
+
+### 4. Configure Power Switch in Home Assistant
+
+Ensure you have a switch entity in Home Assistant that controls the machine's power. Common options:
+
+- **Smart Outlet/Relay**: If using a smart power outlet
+- **IPMI/Redfish**: For datacenter machines
+- **Smart Plug**: Like Tasmota, Zigbee, or Z-Wave devices
+
+Configure the entity ID in your `.env` as `HA_ENTITY` (e.g., `switch.thinkcentre_power`)
+
+### 5. Build and Run
+
+Start the monitoring container:
+
+```bash
+docker compose up -d
+```
+
+The container will:
+- Build from the Dockerfile
+- Start with `restart: unless-stopped` policy
+- Mount logs to a named volume
+- Apply resource limits (0.1 CPU, 64MB memory)
+
+### 6. View Logs
+
+Monitor real-time logs:
+
+```bash
+docker compose logs -f thinkcenter-monitor
+```
+
+Or view persistent logs from the volume:
+
+```bash
+docker volume inspect thinkcenter_logs
+# Look at the Mountpoint directory
+```
+
+### 7. Stop or Restart
+
+Stop the container:
+
+```bash
+docker compose down
+```
+
+Restart the container:
+
+```bash
+docker compose restart thinkcenter-monitor
+```
+
+## Deploying Multiple Instances
+
+To monitor multiple machines:
+
+### For Machine 2:
+
+Create a separate directory:
+
+```bash
+mkdir thinkcentre-watchdog-machine2
+cd thinkcentre-watchdog-machine2
+
+# Copy files
+cp /path/to/original/* .
+
+# Create unique .env
+cp .env.example .env
+
+# Edit .env for machine 2
+nano .env
+# Change: HA_ENTITY=switch.machine2_power
+# Change: TARGET_URL to machine 2's service URL
+```
+
+Then run:
+
+```bash
+docker compose up -d
+```
+
+### Using Namespace (Alternative)
+
+Or manage from one directory with unique service names:
+
+```bash
+docker compose -f docker-compose.yml -f docker-compose.machine2.yml up -d
+```
+
+## Configuration Variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `TARGET_URL` | `http://localhost:8080` | Service URL to monitor |
+| `HA_URL` | `http://homeassistant:8123` | Home Assistant base URL |
+| `HA_TOKEN` | (required) | Home Assistant long-lived access token |
+| `HA_ENTITY` | `switch.thinkcentre_power` | Home Assistant switch entity ID |
+| `GRACE_PERIOD` | `300` | Seconds to wait before power-cycling (5 minutes) |
+| `CHECK_INTERVAL` | `30` | Seconds between health checks |
+
+## Troubleshooting
+
+### Container won't start
+
+Check if `HA_TOKEN` is set:
+```bash
+docker compose config | grep HA_TOKEN
+```
+
+### No logs appearing
+
+Check the volume mount:
+```bash
+docker volume ls | grep thinkcenter_logs
+docker volume inspect thinkcenter_logs
+```
+
+### Power-cycle not triggering
+
+1. Verify HA_TOKEN is valid (check Home Assistant logs)
+2. Confirm HA_ENTITY exists in Home Assistant
+3. Check network connectivity: `docker compose exec thinkcenter-monitor curl -v http://homeassistant:8123`
+
+### Service not responding correctly
+
+Test the target URL directly:
+```bash
+docker compose exec thinkcenter-monitor curl -v http://your-service:8080
+```
+
+## How It Works
+
+1. **Health Check**: Every `CHECK_INTERVAL` seconds, HTTP response code is checked
+2. **Grace Period**: First 502 error triggers a 5-minute window for recovery
+3. **Recovery Detection**: If service returns non-502 during grace period, error resets
+4. **Power Cycle**: After grace period expires with continued 502s, power cycle triggers:
+   - Send turn_off to HA switch entity
+   - Wait 10 seconds
+   - Send turn_on to HA switch entity
+5. **Logging**: All events timestamped and logged to `/var/log/thinkcenter_monitor.log`
+
+## Resource Limits
+
+- CPU: 0.1 cores (limited to prevent resource hogging)
+- Memory: 64MB (minimal requirements for bash + curl)
+- Logging: JSON file driver, max 10MB per file, keeps 3 files (30MB total)
+
+## Debugging
+
+Enable verbose output by checking logs with:
+
+```bash
+docker compose logs --tail 50 thinkcenter-monitor
+```
+
+To test the script locally (without Docker):
+
+```bash
+bash thinkcenter_monitor.sh
+```
+
+## License
+
+Monitoring solution for Thinkcentre machines.
+
+## Support
+
+For issues or improvements, check the logs first and verify all environment variables are correctly set in your `.env` file.

docker-compose.yml

@@ -0,0 +1,35 @@
+version: '3.8'
+
+services:
+  thinkcenter-monitor:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: thinkcenter-monitor
+    restart: unless-stopped
+    
+    environment:
+      TARGET_URL: ${TARGET_URL}
+      HA_URL: ${HA_URL}
+      HA_TOKEN: ${HA_TOKEN}
+      HA_ENTITY: ${HA_ENTITY}
+      GRACE_PERIOD: ${GRACE_PERIOD}
+      CHECK_INTERVAL: ${CHECK_INTERVAL}
+      LOG_FILE: /var/log/thinkcenter_monitor.log
+    
+    volumes:
+      - ./logs:/var/log
+    
+    # Resource limits
+    deploy:
+      resources:
+        limits:
+          cpus: '0.1'
+          memory: 64M
+    
+    # JSON file logging
+    logging:
+      driver: json-file
+      options:
+        max-file: '3'
+        max-size: '10m'

thinkcenter_monitor.sh

@@ -0,0 +1,146 @@
+#!/bin/bash
+
+# Thinkcentre Monitor - Kubernetes Machine Health Monitor with Home Assistant Integration
+# Detects hung machines (502 errors) and auto-reboots them via Home Assistant
+
+# Configuration from environment variables with sensible defaults
+TARGET_URL="${TARGET_URL:-http://localhost:8080}"
+HA_URL="${HA_URL:-http://homeassistant:8123}"
+HA_TOKEN="${HA_TOKEN}"
+HA_ENTITY="${HA_ENTITY:-switch.thinkcentre_power}"
+LOG_FILE="${LOG_FILE:-/var/log/thinkcenter_monitor.log}"
+GRACE_PERIOD="${GRACE_PERIOD:-300}"  # 5 minutes in seconds
+CHECK_INTERVAL="${CHECK_INTERVAL:-30}"  # 30 seconds between checks
+
+# State variables
+ERROR_START_TIME=""
+IN_GRACE_PERIOD=false
+LAST_RESPONSE_CODE=""
+
+# Validate required configuration
+if [[ -z "$HA_TOKEN" ]]; then
+    echo "ERROR: HA_TOKEN environment variable is not set. Exiting." | tee -a "$LOG_FILE"
+    exit 1
+fi
+
+# Initialize log file
+mkdir -p "$(dirname "$LOG_FILE")"
+touch "$LOG_FILE"
+
+log() {
+    local message="$1"
+    local timestamp=$(date '+%Y-%m-%d %H:%M:%S')
+    echo "[$timestamp] $message" | tee -a "$LOG_FILE"
+}
+
+check_target() {
+    # Use curl to get HTTP response code without following redirects
+    local response_code=$(curl -s -o /dev/null -w "%{http_code}" -m 5 "$TARGET_URL" 2>/dev/null)
+    echo "$response_code"
+}
+
+trigger_power_cycle() {
+    local entity="$1"
+    
+    log "ALERT: Triggering power cycle for entity: $entity"
+    
+    # Turn off
+    log "Sending turn_off request to Home Assistant..."
+    curl -s -X POST \
+        -H "Authorization: Bearer $HA_TOKEN" \
+        -H "Content-Type: application/json" \
+        -d "{\"entity_id\": \"$entity\"}" \
+        "$HA_URL/api/services/switch/turn_off" > /dev/null 2>&1
+    
+    if [[ $? -eq 0 ]]; then
+        log "Turn off request sent successfully"
+    else
+        log "ERROR: Failed to send turn_off request"
+    fi
+    
+    # Wait 10 seconds
+    log "Waiting 10 seconds before power-on..."
+    sleep 10
+    
+    # Turn on
+    log "Sending turn_on request to Home Assistant..."
+    curl -s -X POST \
+        -H "Authorization: Bearer $HA_TOKEN" \
+        -H "Content-Type: application/json" \
+        -d "{\"entity_id\": \"$entity\"}" \
+        "$HA_URL/api/services/switch/turn_on" > /dev/null 2>&1
+    
+    if [[ $? -eq 0 ]]; then
+        log "Turn on request sent successfully"
+        log "Power cycle completed for $entity"
+    else
+        log "ERROR: Failed to send turn_on request"
+    fi
+    
+    # Reset state
+    ERROR_START_TIME=""
+    IN_GRACE_PERIOD=false
+}
+
+log "=== Thinkcentre Monitor Started ==="
+log "Configuration:"
+log "  TARGET_URL: $TARGET_URL"
+log "  HA_URL: $HA_URL"
+log "  HA_ENTITY: $HA_ENTITY"
+log "  GRACE_PERIOD: ${GRACE_PERIOD}s ($(( GRACE_PERIOD / 60 )) minutes)"
+log "  CHECK_INTERVAL: ${CHECK_INTERVAL}s"
+
+# Main monitoring loop
+while true; do
+    RESPONSE_CODE=$(check_target)
+    
+    # Log all responses
+    log "HTTP Response: $RESPONSE_CODE"
+    
+    if [[ "$RESPONSE_CODE" == "502" ]]; then
+        # 502 Bad Gateway error detected
+        
+        if [[ -z "$ERROR_START_TIME" ]]; then
+            # First 502 error - start grace period
+            ERROR_START_TIME=$(date +%s)
+            IN_GRACE_PERIOD=true
+            log "502 error detected - starting 5-minute grace period (recovery window for deployment scenarios)"
+        else
+            # Already in grace period - check if it has expired
+            CURRENT_TIME=$(date +%s)
+            ELAPSED=$((CURRENT_TIME - ERROR_START_TIME))
+            
+            if [[ $ELAPSED -ge $GRACE_PERIOD ]]; then
+                # Grace period expired - trigger power cycle
+                log "Grace period expired after ${ELAPSED}s. Service still unavailable."
+                trigger_power_cycle "$HA_ENTITY"
+                ERROR_START_TIME=""
+                IN_GRACE_PERIOD=false
+            else
+                # Still within grace period
+                REMAINING=$((GRACE_PERIOD - ELAPSED))
+                log "Still in grace period. Service recovery window: ${REMAINING}s remaining"
+            fi
+        fi
+    else
+        # Service is responding (any code other than 502)
+        if [[ "$IN_GRACE_PERIOD" == true ]]; then
+            # Service recovered during grace period
+            CURRENT_TIME=$(date +%s)
+            RECOVERY_TIME=$((CURRENT_TIME - ERROR_START_TIME))
+            log "Service recovered during grace period after ${RECOVERY_TIME}s. Resetting error state."
+            ERROR_START_TIME=""
+            IN_GRACE_PERIOD=false
+        elif [[ "$RESPONSE_CODE" != "000" ]]; then
+            # Service is healthy (not a timeout)
+            if [[ -n "$LAST_RESPONSE_CODE" && "$LAST_RESPONSE_CODE" != "$RESPONSE_CODE" ]]; then
+                log "Service status changed from $LAST_RESPONSE_CODE to $RESPONSE_CODE"
+            fi
+        fi
+    fi
+    
+    LAST_RESPONSE_CODE="$RESPONSE_CODE"
+    
+    # Wait for next check
+    sleep "$CHECK_INTERVAL"
+done