Everything to verify before deploying obleth to production: datastores, secrets, TLS, capacity, monitoring, and backup.
This checklist covers the minimum steps to harden an obleth deployment for production traffic.
OBLETH_ADMIN_TOKEN: strong random token (≥32 chars). Use a Kubernetes Secret or Vault. Never commit to source control.DASHBOARD_SESSION_SECRET: change from the default dev-session-secret-change-in-production.DASHBOARD_PASSWORD: change from default obleth.obleth.obleth.api_key and MCP auth_header values: stored in Postgres. Ensure database-at-rest encryption.:8080) reachable only from HAProxy/Ingress, not from the internet.:9090) not publicly accessible — restrict to internal network or VPN. The admin token is the only auth.:9091) accessible only to your Prometheus scraper.OBLETH_GLOBAL_MAX_IN_FLIGHT to match real inference backend concurrency (start conservative: 64, increase based on queue depth).hpa.enabled=true); set maxReplicas based on traffic patterns.OBLETH_BROWNOUT_WAIT_MS appropriate to your SLA.OBLETH_FAIL_OPEN: true (keep serving under Redis failure) or false (strict budget enforcement).OBLETH_WAL_PATH to a persistent volume path (not /tmp). The WAL must survive pod restarts.:9091/metrics.obleth_queue_depth > threshold (admission saturation).obleth_telemetry_dropped > 0 (WAL pressure).obleth_requests_total{status="5xx"} spike (upstream failures).serviceMonitor.enabled=true if using Prometheus Operator.OBLETH_OTEL_ENDPOINT for distributed tracing.input_cost_per_token and output_cost_per_token.tokens_per_minute quotas initially; increase based on observed usage.GET /api/v1/audit.