Get complexity classifier status

Returns the runtime status of the semantic complexity classifier (disabled, warming, ready, or failed), including warmup progress and whether a previous generation is still serving. When the llm fallback block is configured, also returns its readiness and the shipped default classification prompt.

GET /api/routing/complexity-analyzer-status

Error

A valid request URL is required to generate request examples

200

{
  "state": "disabled",
  "loaded": 123,
  "total": 123,
  "serving_previous": true,
  "failure_reason": "authentication",
  "error": "<string>",
  "cached_phrases": 123,
  "storage_mode": "embedded",
  "namespace": "<string>",
  "llm": {
    "state": "disabled"
  },
  "llm_default_prompt": "<string>"
}

Authorizations

BearerAuthBasicAuthApiKeyAuth

Authorization · string · header · required

Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with sk-bf-) can also be passed here.

Response

200

application/json

Complexity classifier status retrieved successfully

Runtime status of the semantic complexity classifier and, when configured, the LLM fallback classifier. Never contains phrases, embeddings, or provider secrets.

state · enum<string>

disabled = no embedding configuration; warming = reference phrases are being embedded; ready = serving the current configuration; failed = the desired configuration failed to warm

Available options: disabled, warming, ready, failed

loaded · integer

Reference phrases embedded so far in the current warmup

total · integer

Total reference phrases to embed in the current warmup

serving_previous · boolean

When true with state=failed, the previous generation is still serving while the new one failed to warm

failure_reason · enum<string>

Category of a warmup failure when state=failed. Provider and backend error bodies stay in server logs; this bounded vocabulary is what status clients receive.

Available options: authentication, model_unavailable, rate_limited, timeout, provider_unavailable, vector_store_unavailable, invalid_response, unknown

error · string

Warmup failure detail when state=failed

cached_phrases · integer

How many phrase vectors the gateway currently holds in process for the configured provider and model. The cache is in-process only, since vectors cannot be read back out of a vector store, so a restart empties it while the saved phrases look unchanged. Zero means the next save re-embeds every phrase regardless of what changed.

storage_mode · enum<string>

Where exemplar vectors are actually kept, which is not always what was configured. semantic.vector_store=vector_store degrades to embedded whenever no top-level vector store is configured, so this reports what is in force rather than what was asked for. Absent until a store has been resolved.

Available options: embedded, vector_store

namespace · string

The fingerprinted namespace the serving generation queries, for example BifrostComplexityRouter_. The backend holds no phrase text, so this is the only handle on the records the classifier owns in a shared vector store. Absent while nothing is serving.

llm · object

Always present in the response. state is disabled when no llm block is configured.

Show child attributes

llm_default_prompt · string

The shipped classification guidance, served so a configuration client can seed its prompt editor and offer a reset without holding a copy that drifts from the gateway's. Always present in the response, regardless of whether an llm block is configured.