How to Prevent Runaway Automations in OpenClaw

# List all active automations:
curl http://localhost:3000/api/automations

# Red flags:
# - No max_iterations set
# - No timeout
# - Checks external condition (API, file, etc)
# - Triggers on every message
# - Calls another automation

# Example dangerous automation:
# while (api.status != "complete") {
#   wait(30);
#   checkStatus();
# }
# ← If "complete" never comes, this runs forever

# In config/automations.yaml:
automations:
  - name: status-checker
    max_iterations: 50  # Stop after 50 loops
    on_limit_reached: alert_and_stop

  - name: data-processor
    max_iterations: 100
    on_limit_reached: alert_and_continue  # Log but don't stop

  - name: one-time-task
    max_iterations: 1  # Not a loop at all

# In config/automations.yaml (continued):
guardrails:
  global:
    max_tokens_per_automation_run: 100000
    max_tokens_per_hour: 500000

  per_automation:
    status-checker:
      max_tokens_per_run: 10000
    data-processor:
      max_tokens_per_run: 50000

  on_token_limit:
    action: pause_and_alert
    message: "Automation exceeded token budget"

# In config/automations.yaml (continued):
timeouts:
  global:
    max_runtime_minutes: 30  # Kill any automation after 30min

  per_automation:
    status-checker:
      max_runtime_minutes: 10
    long-runner:
      max_runtime_minutes: 120  # 2 hours max

  on_timeout:
    action: stop_and_alert
    save_partial_results: true

# In config/automations.yaml (continued):
kill_switches:
  - type: manual
    endpoint: POST /api/automations/emergency-stop
    requires_auth: true

  - type: cost_threshold
    daily_cost_limit: 50.00  # USD
    action: pause_all_automations

  - type: error_rate
    threshold: 0.5  # 50% of iterations fail
    window_minutes: 10
    action: pause_automation

# Create emergency stop script:
# emergency-stop.sh
curl -X POST http://localhost:3000/api/automations/emergency-stop \
  -H "Authorization: Bearer $ADMIN_TOKEN"

# In config/alerts.yaml:
automation_alerts:
  - trigger: iteration_limit_reached
    channel: email
    recipients: ["admin@company.com"]

  - trigger: token_budget_exceeded
    channel: slack
    webhook: $SLACK_WEBHOOK

  - trigger: timeout
    channel: sms  # Critical
    phone: "+1-555-0123"

  - trigger: error_rate_high
    channel: email
    threshold: 0.3  # 30% errors

# Create test automation that intentionally loops:
# test-automations/runaway-test.yaml
name: runaway-test
max_iterations: 5  # Should stop here
script: |
  iteration = 0
  while true:
    iteration += 1
    log(f"Iteration {iteration}")
    sleep(1)

# Run test:
npm run automation -- runaway-test

# Expected: Stops at 5 iterations with alert
# If it doesn't stop, your guardrails aren't working