Xinference failed-request counter

Counter of FAILED model requests. Worth knowing what it does not include: a request rejected by the rate limiter before it reaches the model is counted by xinference:banned_ips_total / xinference:banned_keys_total instead, so a load-shedding event shows up as a banned-IP rise and a flat error count. Xinference main (xorbitsai/inference), read 2026-10-05. NOT ON BY DEFAULT on the worker: the /metrics endpoint is only mounted when XINFERENCE_DISABLE_METRICS is unset AND a metrics exporter host or port is supplied; otherwise launch_metrics_export_server() is never called and the endpoint does not exist. Supervisor-side metrics are deregistered from the worker's registry on purpose (launch_metrics_export_server removes _SUPERVISOR_ONLY_METRICS), so the worker endpoint carries only worker metrics and the supervisor endpoint only supervisor metrics. aioprometheus, not prometheus_client: counters do not auto-suffix _total the way prometheus_client does, so two of these names end in _counter and three do not - match on the literal name.