Scans ~/.openclaw/agents/main/sessions/ for recent LLM API error patterns (500 errors, token failures, cooldowns, service_busy) and produces a JSON health report.
js
const { checkApiHealth } = require('./skills/api-health-monitor');
const report = await checkApiHealth();
// { healthy: bool, errors: [...], recommendation: string }
FieldTypeDescriptionhealthybooleantrue if no errors founderrorsarray[{ type, message, count, lastSeen }]``recommendationstringSuggested action based on findings