mistral-incident-runbook

# Mistral AI Incident Runbook ## Overview Rapid incident response procedures for Mistral AI integration failures. Covers severity classification, quick triage script, decision tree, per-error mitigations, communication templates, and postmortem process. ## Severity Levels | Level | Definition | Response Time | Example | |-------|------------|---------------|---------| | P1 | Complete outage | < 15 min | All Mistral requests failing | | P2 | Degraded service | < 1 hour | High latency, partial 429s | | P3 | Minor impact | < 4 hours | Occasional errors, non-critical feature | | P4 | No user impact | Next business day | Monitoring gaps, docs | ## Quick Triage Script ```bash #!/bin/bash set -euo pipefail echo "=== Mistral AI Quick Triage ===" echo "Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ)" # 1. API health echo -e "\n1. Mistral API status:" HTTP=$(curl -s -o /dev/null -w "%{http_code}" \ -H "Authorization: Bearer ${MISTRAL_API_KEY}" \ https://api.mistral.ai/v1/models 2>/dev/null) echo " HTTP: $HTTP" case $HTTP in 200) echo " OK — API is reachable" ;; 401) echo " AUTH FAILURE — API key invalid or revoked" ;; 429) echo " RATE LIMITED — check workspace limits" ;; 5*) echo " SERVER ERROR — Mistral service issue" ;; 000) echo " NETWORK ERROR — cannot reach api.mistral.ai" ;; esac # 2. Our service health echo -e "\n2. App health endpoint:" curl -sf https://yourapp.com/health 2>/dev/null | jq '.services.mistral' || echo " UNREACHABLE" # 3. Error rate (...