config.example.yaml

# Example Configuration File for Python-Script-Runner
# Copy to config.yaml and customize for your use case

# ============================================================================
# ALERT DEFINITIONS
# ============================================================================
alerts:
  # Alert on high CPU usage
  - name: cpu_high
    condition: cpu_max > 80
    channels: [slack, stdout]
    severity: WARNING
    throttle_seconds: 300
  
  # Alert on memory spike (rapid increase)
  - name: memory_spike
    condition: memory_max_mb > 2048
    channels: [email, slack]
    severity: CRITICAL
    throttle_seconds: 600
  
  # Alert on script timeout risk
  - name: timeout_risk
    condition: execution_time_seconds > 240
    channels: [slack]
    severity: INFO
    throttle_seconds: 300
  
  # Alert on script failure
  - name: script_failed
    condition: exit_code != 0
    channels: [email, slack]
    severity: CRITICAL
    throttle_seconds: 300
  
  # Alert on high page faults (potential memory issues)
  - name: memory_pressure
    condition: page_faults_major > 100
    channels: [slack]
    severity: WARNING
    throttle_seconds: 300

# ============================================================================
# PERFORMANCE GATES FOR CI/CD
# ============================================================================
performance_gates:
  # CPU max should not exceed 90%
  - metric_name: cpu_max
    max_value: 90
    comparator: max
  
  # Memory max should not exceed 1GB
  - metric_name: memory_max_mb
    max_value: 1024
    comparator: max
  
  # Execution time should not exceed 5 minutes
  - metric_name: execution_time_seconds
    max_value: 300
    comparator: max
  
  # Average CPU should stay reasonable
  - metric_name: cpu_avg
    max_value: 60
    comparator: avg

# ============================================================================
# NOTIFICATION CHANNEL CONFIGURATIONS
# ============================================================================
notifications:
  # Slack webhook configuration
  slack:
    webhook_url: "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
    # You can use environment variables: ${SLACK_WEBHOOK_URL}
  
  # Email configuration (SMTP)
  email:
    smtp_server: "smtp.gmail.com"
    smtp_port: 587
    from: "alerts@example.com"
    to:
      - "team@example.com"
      - "ops@example.com"
    username: "your-email@gmail.com"
    # Use environment variable for password: ${GMAIL_APP_PASSWORD}
    password: "your-app-password-here"
    use_tls: true
  
  # Custom webhook endpoint
  webhook:
    url: "https://your-monitoring-system.com/api/alerts"
    headers:
      Authorization: "Bearer YOUR_TOKEN_HERE"
      Content-Type: "application/json"

# ============================================================================
# ALERT EXAMPLES FOR DIFFERENT SCENARIOS
# ============================================================================

# Example: Long-running data processing job
# alerts:
#   - name: processing_slow
#     condition: execution_time_seconds > 1800  # 30 minutes
#     channels: [slack]
#     severity: INFO
#     throttle_seconds: 600
#
#   - name: processing_memory_issue
#     condition: memory_delta > 500  # 500MB increase
#     channels: [email, slack]
#     severity: WARNING
#     throttle_seconds: 900

# Example: Machine Learning training job
# alerts:
#   - name: gpu_underutilized
#     condition: cpu_max < 10
#     channels: [slack]
#     severity: INFO
#     throttle_seconds: 300
#
#   - name: training_diverging
#     condition: execution_time_seconds > 3600 and memory_max_mb > 8192
#     channels: [email, slack]
#     severity: CRITICAL
#     throttle_seconds: 300

# Example: Test suite execution
# performance_gates:
#   - metric_name: execution_time_seconds
#     max_value: 600  # Tests should complete in 10 minutes
#   - metric_name: memory_max_mb
#     max_value: 512  # Tests should not use more than 512MB
#   - metric_name: exit_code
#     min_value: 0  # Must succeed

# ============================================================================
# COMMON METRIC CONDITIONS
# ============================================================================
# Available metrics for conditions:
# - execution_time_seconds: Total execution time
# - exit_code: Process exit code (0 = success)
# - success: Boolean success indicator
# - cpu_max, cpu_avg, cpu_min: CPU usage percentages
# - memory_max_mb, memory_avg_mb, memory_min_mb: Memory in MB
# - user_time_seconds: User time
# - system_time_seconds: System time
# - page_faults_major: Major page faults (disk swaps)
# - page_faults_minor: Minor page faults
# - voluntary_context_switches: Context switches requested
# - involuntary_context_switches: Context switches forced by kernel
# - stdout_lines: Number of output lines
# - stderr_lines: Number of error lines
#
# Examples of conditions:
# - cpu_max > 80
# - memory_max_mb > 2048
# - execution_time_seconds > 300 and success == false
# - page_faults_major > 50
# - exit_code != 0