.env.monitoring.example

# FlakeGuard Monitoring Configuration
# Copy to .env.monitoring and customize for your environment

# ============================================================================
# Metrics Collection
# ============================================================================
METRICS_ENABLED=true
METRICS_PORT=9090
METRICS_PATH=/metrics
METRICS_COLLECTION_INTERVAL=15000

# ============================================================================
# Health Checks
# ============================================================================
HEALTH_CHECK_ENABLED=true
HEALTH_CHECK_PORT=3000
HEALTH_CHECK_TIMEOUT=5000
HEALTH_CHECK_DATABASE_ENABLED=true
HEALTH_CHECK_REDIS_ENABLED=true

# ============================================================================
# SLO Configuration
# ============================================================================
SLO_API_AVAILABILITY_TARGET=0.999
SLO_INGESTION_LATENCY_TARGET=30
SLO_PARSE_SUCCESS_RATE_TARGET=0.99
SLO_CHECK_RUN_DELIVERY_TARGET=60
SLO_ERROR_BUDGET_WINDOW=2592000  # 30 days in seconds

# ============================================================================
# Alerting Configuration
# ============================================================================
ALERTS_ENABLED=true
ALERT_FAST_BURN_MULTIPLIER=1440  # For API availability (30min to exhaust budget)
ALERT_SLOW_BURN_MULTIPLIER=6     # For sustained issues (5 days to exhaust budget)

# ============================================================================
# Prometheus Configuration
# ============================================================================
PROMETHEUS_URL=http://localhost:9090
PROMETHEUS_RETENTION_TIME=30d
PROMETHEUS_RETENTION_SIZE=50GB
PROMETHEUS_SCRAPE_INTERVAL=15s

# ============================================================================
# Alertmanager Configuration
# ============================================================================
ALERTMANAGER_URL=http://localhost:9093
ALERTMANAGER_GROUP_WAIT=30s
ALERTMANAGER_GROUP_INTERVAL=5m
ALERTMANAGER_REPEAT_INTERVAL=12h

# ============================================================================
# Notification Channels
# ============================================================================

# Slack Integration
SLACK_ENABLED=false
SLACK_WEBHOOK_URL=https://hooks.slack.com/services/EXAMPLE/EXAMPLE/EXAMPLE
SLACK_CHANNEL_CRITICAL=#sre-alerts
SLACK_CHANNEL_WARNING=#flakeguard-alerts
SLACK_CHANNEL_INFO=#flakeguard-info

# Email Notifications
EMAIL_ENABLED=false
EMAIL_SMTP_HOST=smtp.company.com
EMAIL_SMTP_PORT=587
EMAIL_SMTP_USERNAME=flakeguard-alerts@company.com
EMAIL_SMTP_PASSWORD=your-smtp-password
EMAIL_FROM=flakeguard-alerts@company.com
EMAIL_TO_CRITICAL=sre-oncall@company.com
EMAIL_TO_WARNING=dev-team@company.com

# PagerDuty Integration
PAGERDUTY_ENABLED=false
PAGERDUTY_INTEGRATION_KEY=your-pagerduty-integration-key
PAGERDUTY_ROUTING_KEY=your-routing-key

# OpsGenie Integration  
OPSGENIE_ENABLED=false
OPSGENIE_API_KEY=your-opsgenie-api-key
OPSGENIE_TEAM=database-team

# ============================================================================
# Grafana Configuration
# ============================================================================
GRAFANA_URL=http://localhost:3001
GRAFANA_ADMIN_USERNAME=admin
GRAFANA_ADMIN_PASSWORD=admin123
GRAFANA_DEFAULT_THEME=dark
GRAFANA_ALLOW_SIGN_UP=false

# Dashboard Settings
GRAFANA_AUTO_REFRESH=30s
GRAFANA_DEFAULT_TIME_RANGE=1h

# ============================================================================
# Resource Monitoring
# ============================================================================

# Memory Thresholds (MB)
MEMORY_WARNING_THRESHOLD=512
MEMORY_CRITICAL_THRESHOLD=1024

# CPU Thresholds (%)
CPU_WARNING_THRESHOLD=70
CPU_CRITICAL_THRESHOLD=90

# Disk Thresholds (%)
DISK_WARNING_THRESHOLD=80
DISK_CRITICAL_THRESHOLD=95

# ============================================================================
# Business Metrics
# ============================================================================

# Repository Activity
ACTIVE_REPO_WINDOW=7d  # Consider repos active if they had activity in last 7 days

# Flake Detection
FLAKE_RATE_WARNING_THRESHOLD=10   # Alert if detecting >10 flakes/hour
FLAKE_RATE_CRITICAL_THRESHOLD=50  # Alert if detecting >50 flakes/hour

# Queue Monitoring
QUEUE_WARNING_DEPTH=100    # Alert if queue depth > 100
QUEUE_CRITICAL_DEPTH=500   # Alert if queue depth > 500

# ============================================================================
# Development/Testing
# ============================================================================

# Test Environment Settings (set to true for development)
DISABLE_CRITICAL_ALERTS=false
DISABLE_PAGING_ALERTS=false
MOCK_EXTERNAL_SERVICES=false
METRICS_DEBUG_MODE=false

# Test Data Generation
GENERATE_TEST_METRICS=false
TEST_METRICS_INTERVAL=10000  # Generate test metrics every 10s

# ============================================================================
# Security
# ============================================================================

# Metrics endpoint authentication (if needed)
METRICS_AUTH_ENABLED=false
METRICS_AUTH_TOKEN=your-secure-metrics-token

# Dashboard access control
DASHBOARD_AUTH_ENABLED=true
DASHBOARD_VIEWER_PASSWORD=viewer123
DASHBOARD_EDITOR_PASSWORD=editor123

# ============================================================================
# Deployment Configuration
# ============================================================================

# Environment
ENVIRONMENT=production  # development, staging, production
CLUSTER_NAME=production
REGION=us-west-2

# Service Discovery
SERVICE_DISCOVERY=static  # static, kubernetes, consul
KUBERNETES_NAMESPACE=flakeguard

# External Labels (added to all metrics)
SERVICE_NAME=flakeguard
SERVICE_VERSION=1.0.0
TEAM=engineering

# ============================================================================
# Performance Tuning
# ============================================================================

# Metrics Collection
METRICS_BATCH_SIZE=1000
METRICS_FLUSH_INTERVAL=5000
HIGH_CARDINALITY_METRICS_ENABLED=false

# Alert Evaluation
ALERT_EVALUATION_INTERVAL=15s
ALERT_QUEUE_CAPACITY=10000

# Dashboard Performance
DASHBOARD_QUERY_TIMEOUT=30s
DASHBOARD_MAX_DATA_POINTS=11000

# ============================================================================
# Backup and Retention
# ============================================================================

# Prometheus Data
PROMETHEUS_BACKUP_ENABLED=true
PROMETHEUS_BACKUP_RETENTION=90d
PROMETHEUS_BACKUP_SCHEDULE="0 2 * * *"  # Daily at 2 AM

# Grafana Dashboards
GRAFANA_BACKUP_ENABLED=true
GRAFANA_BACKUP_RETENTION=30d

# Alert History
ALERT_HISTORY_RETENTION=90d