my system is having trouble with identifying models:
luok@hublx in ~ via  v3.13.7 as 🧙
╰─λ curl 192.168.0.169:40114/internal/health
{"status":"healthy"}⏎
╭─luok@hublx in ~ via  v3.13.7 as 🧙 took 0s
╰─λ curl 192.168.0.169:40114/internal/status/endpoints
{"timestamp":"2025-12-04T21:15:44.100049657+01:00","endpoints":[{"name":"local-llamacpp","type":"llamacpp","status":"healthy","health_check":"28s ago","response_time":"1ms","success_rate":"N/A","priority":100,"model_count":0,"request_count":0}],"total_count":1,"healthy_count":1,"routable_count":1}

╭─luok@hublx in ~ via  v3.13.7 as 🧙 took 0s
╰─λ curl 192.168.0.169:40114/internal/status/models
{"timestamp":"2025-12-04T21:15:59.88380477+01:00","models_by_family":{},"recent_models":[],"total_models":0,"total_families":0,"total_endpoints":0}

But:
curl 192.168.0.169:8080/models
{"models":[{"name":"Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002.gguf","model":"Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002.gguf","modified_at":"","size":"","digest":"","type":"model","description":"","tags":[""],"capabilities":["completion"],"parameters":"","details":{"parent_model":"","format":"gguf","family":"","families":[""],"parameter_size":"","quantization_level":""}}],"object":"list","data":[{"id":"Qwen3-Next-80B-A3B-Instruct-UD-Q8_K_XL-00001-of-00002.gguf","object":"model","created":1764879484,"owned_by":"llamacpp","meta":{"vocab_type":2,"n_vocab":151936,"n_ctx_train":262144,"n_embd":2048,"n_params":79674391296,"size":85436689408}}]}

My config :

server:
host: "0.0.0.0"
port: 40114

proxy:
engine: "sherpa"
profile: "auto"

llama.cpp backend discovery

discovery:
type: static
static:
endpoints:

• url: "http://192.168.0.169:8080"
  name: "local-llamacpp"
  type: "llamacpp"
  priority: 100
  model_url: "/v1/models" # OpenAI-compatible endpoint
  health_check_url: "/health" # llama.cpp health endpoint
  check_interval: 2s
  check_timeout: 1s

model_registry:
enable_unifier: true

logging:
level: "info" # debug, info, warn, error