groups: - name: agentidp_alerts rules: - alert: AuthFailureSpike expr: rate(agentidp_http_requests_total{status_code="401"}[5m]) > 0.5 for: 2m labels: { severity: warning } annotations: summary: "Auth failure spike detected" description: "More than 0.5 auth failures/sec over the past 2 minutes." - alert: RateLimitExhaustion expr: rate(agentidp_http_requests_total{status_code="429"}[5m]) > 0.2 for: 2m labels: { severity: warning } annotations: summary: "Rate limit exhaustion spike" description: "Sustained rate limit rejections over the past 2 minutes." - alert: AnomalousTokenIssuance expr: rate(agentidp_tokens_issued_total[5m]) > 10 for: 5m labels: { severity: warning } annotations: summary: "Anomalous token issuance rate" description: "More than 10 tokens/sec issued over the past 5 minutes." - alert: WebhookDeadLetterAccumulating expr: increase(agentidp_webhook_dead_letters_total[1h]) > 10 for: 0m labels: { severity: critical } annotations: summary: "Webhook dead-letter accumulation" description: "More than 10 webhook deliveries moved to dead-letter in the past hour." - alert: AuditChainIntegrityFailed expr: agentidp_audit_chain_integrity == 0 for: 0m labels: { severity: critical } annotations: summary: "Audit chain integrity failure" description: "Audit chain verification failed — possible log tampering detected." - alert: CredentialExpiryApproaching expr: increase(agentidp_credentials_expiring_soon_total[1h]) > 0 for: 0m labels: { severity: info } annotations: summary: "Credentials expiring soon" description: "One or more agent credentials will expire within 7 days."