pup auth login

pup monitors list
pup monitors list --tags "team:platform"
pup monitors list --status "Alert"

pup monitors get <id> --json

pup monitors create \
  --name "High CPU on web servers" \
  --type "metric alert" \
  --query "avg(last_5m):avg:system.cpu.user{env:prod} > 80" \
  --message "CPU above 80% @slack-ops"

# Mute with duration
pup monitors mute --id 12345 --duration 1h

# Or mute with specific end time
pup monitors mute --id 12345 --end "2024-01-15T18:00:00Z"

# Unmute
pup monitors unmute --id 12345

# WRONG - will flap constantly
query = "avg(last_1m):avg:system.cpu.user{*} > 50"  # ❌ Too sensitive

# CORRECT - stable alerting
query = "avg(last_5m):avg:system.cpu.user{env:prod} by {host} > 80"  # ✅ Reasonable window

# WRONG - alerts on everything
query = "avg(last_5m):avg:system.cpu.user{*} > 80"  # ❌ No scope

# CORRECT - scoped to what matters
query = "avg(last_5m):avg:system.cpu.user{env:prod,service:api} by {host} > 80"  # ✅

monitor = {
    "query": "avg(last_5m):avg:system.cpu.user{env:prod} > 80",
    "options": {
        "thresholds": {
            "critical": 80,
            "critical_recovery": 70,  # ✅ Prevents flapping
            "warning": 60,
            "warning_recovery": 50
        }
    }
}

message = """
## High CPU Alert

Host: {{host.name}}
Current Value: {{value}}
Threshold: {{threshold}}

### Runbook
1. Check top processes: `ssh {{host.name}} 'top -bn1 | head -20'`
2. Check recent deploys
3. Scale if needed

@slack-ops @pagerduty-oncall
"""

def safe_mark_monitor_for_deletion(monitor_id: str, client) -> bool:
    """Mark monitor instead of deleting."""
    monitor = client.get_monitor(monitor_id)
    name = monitor.get("name", "")
    
    if "[MARKED FOR DELETION]" in name:
        print(f"Already marked: {name}")
        return False
    
    new_name = f"[MARKED FOR DELETION] {name}"
    client.update_monitor(monitor_id, {"name": new_name})
    print(f"✓ Marked: {new_name}")
    return True

# Find monitors without owners
pup monitors list --json | jq '.[] | select(.tags | contains(["team:"]) | not) | {id, name}'

# Find noisy monitors (high alert count)
pup monitors list --json | jq 'sort_by(.overall_state_modified) | .[:10] | .[] | {id, name, status: .overall_state}'

# Downtime (preferred)
pup downtime create \
  --scope "env:prod" \
  --monitor-tags "team:platform" \
  --start "2024-01-15T02:00:00Z" \
  --end "2024-01-15T06:00:00Z"