clade-incident-runbook

# Anthropic Incident Runbook ## Overview Respond to Anthropic API incidents in production — outages, sustained 529 errors, authentication failures, and timeouts. Covers status page checking, severity classification, model fallback activation, communication, and post-incident review. ## Step 1: Confirm the Issue ```bash # Check Anthropic status curl -s https://status.anthropic.com/api/v2/status.json | python3 -c " import json, sys d = json.load(sys.stdin) print(f\"Status: {d['status']['description']} ({d['status']['indicator']})\")" # Test API directly curl -s -w "\nHTTP %{http_code} in %{time_total}s\n" \ https://api.anthropic.com/v1/messages \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "claude-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{"model":"claude-haiku-4-5-20251001","max_tokens":5,"messages":[{"role":"user","content":"ping"}]}' ``` ## Step 2: Classify Severity | Symptom | Severity | Action | |---------|----------|--------| | 529 overloaded (intermittent) | Low | SDK auto-retries handle this | | 529 overloaded (sustained 5+ min) | Medium | Switch to fallback model | | 401/403 on all requests | High | API key issue — check console | | All requests timing out | High | Check status page, activate fallback | | Status page shows incident | Varies | Follow status page updates | ## Step 3: Activate Fallback ```typescript async function callWithFallback(params: Anthropic.MessageCreateParams) { try { return await client.messages.create(pa...