#!/bin/bash
echo "=== MaintainX Incident Triage ==="
echo "Time: $(date -u)"

# Check MaintainX API status
echo -e "\n--- API Health ---"
for endpoint in users workorders assets locations; do
  CODE=$(curl -s -o /dev/null -w "%{http_code}" \
    "https://api.getmaintainx.com/v1/$endpoint?limit=1" \
    -H "Authorization: Bearer $MAINTAINX_API_KEY")
  echo "  /$endpoint: HTTP $CODE"
done

# Check your integration service
echo -e "\n--- Integration Service ---"
curl -s http://localhost:3000/health | jq . 2>/dev/null || echo "  Service unreachable"

# Check recent error logs
echo -e "\n--- Recent Errors (last 10 min) ---"
# Adjust for your log system:
# journalctl -u maintainx-sync --since "10 min ago" --no-pager | grep -i error | tail -10

# Generate new key: MaintainX > Settings > Integrations > New Key
# Update in production:
# GCP Secret Manager:
echo -n "NEW_KEY_HERE" | gcloud secrets versions add maintainx-api-key --data-file=-
# Restart service to pick up new key:
gcloud run services update maintainx-integration --region us-central1 --no-traffic

// Immediately reduce request volume
// 1. Enable emergency rate limiting
process.env.MAINTAINX_MAX_REQUESTS_PER_SEC = '1';
// 2. Disable non-critical sync jobs
await disableScheduledJobs(['asset-sync', 'report-generator']);
// 3. Keep only critical work order processing

// Switch to queue-based processing
// Buffer all outgoing requests for replay after recovery
const queue: Array<{ method: string; path: string; body: any }> = [];

function bufferRequest(method: string, path: string, body?: any) {
  queue.push({ method, path, body });
  console.log(`Buffered: ${method} ${path} (queue size: ${queue.length})`);
}

// When MaintainX recovers, replay buffered requests
async function replayQueue(client: MaintainXClient) {
  console.log(`Replaying ${queue.length} buffered requests...`);
  for (const req of queue) {
    await withRetry(() => client.request(req.method, req.path, req.body));
  }
  queue.length = 0;
}

# Run full health check
curl -s http://localhost:3000/health | jq .

# Verify data flow
echo "Work orders created in last hour:"
curl -s "https://api.getmaintainx.com/v1/workorders?createdAtGte=$(date -u -d '1 hour ago' +%Y-%m-%dT%H:%M:%SZ)&limit=5" \
  -H "Authorization: Bearer $MAINTAINX_API_KEY" | jq '.workOrders | length'

# Check for data gaps
echo "Checking sync state..."
cat .maintainx-sync-state.json 2>/dev/null || echo "No sync state file found"

## Incident Report Template

**Date**: YYYY-MM-DD
**Severity**: SEV-X
**Duration**: X hours Y minutes
**Impact**: [What was affected - e.g., "work order sync halted for 2 hours"]

### Timeline
- HH:MM - Alert triggered
- HH:MM - Triage started
- HH:MM - Root cause identified
- HH:MM - Mitigation applied
- HH:MM - Full recovery confirmed

### Root Cause
[Technical explanation]

### Resolution
[What was done to fix it]

### Action Items
- [ ] Implement [specific improvement]
- [ ] Add monitoring for [gap found]
- [ ] Update runbook with [lesson learned]

// Check health every 5 minutes, alert on failure
import cron from 'node-cron';

cron.schedule('*/5 * * * *', async () => {
  try {
    const res = await fetch('http://localhost:3000/health');
    const health = await res.json();
    if (health.status !== 'healthy') {
      await sendPagerDutyAlert({
        severity: 'critical',
        summary: `MaintainX integration degraded: ${JSON.stringify(health.checks)}`,
      });
    }
  } catch {
    await sendPagerDutyAlert({
      severity: 'critical',
      summary: 'MaintainX integration service unreachable',
    });
  }
});