Agent Tests

Fetch one test run. Runs start queued and end passed, failed or error. A simulation run takes minutes, so poll until it finishes.

get/v1/agent/test-runs/{run_id}

Request

  • Base URL
    https://api.fish.audio
  • URL
    https://api.fish.audio/v1/agent/test-runs/{run_id}
  • Auth
    HTTP bearer

Path parameters

run_idstring required

Response

Request fulfilled, document follows

run_idstring required
test_idstring required
agent_idstring required
batch_idstring nullable
test_type'next_reply' | 'tool' | 'simulation' required
repeat_indexinteger

Which repeat of the test in its batch this run is.

status'queued' | 'running' | 'passed' | 'failed' | 'error' required
needs_reviewboolean

The judge could not decide, or a tool call had no mock answer.

errorstring
created_atstring date-time required
started_atstring date-time nullable
finished_atstring date-time nullable
agent_replystring

The reply a scripted test judged.

judge_reasoningstring
config_hashstring

The agent draft's config hash the run tested.

latency_msinteger
channel'web_voice' | 'phone_inbound' | 'phone_outbound' nullable
turns_usedinteger
ended_by'agent' | 'user' | 'transfer' | 'max_turns' | 'timeout' | 'error' nullable

Changes