Get test

from elevenlabs import ElevenLabs
client = ElevenLabs(
    base_url="https://api.elevenlabs.io"
)
client.conversational_ai.tests.get(
    test_id="test_id"
)

{
  "chat_history": [
    {
      "role": "user",
      "time_in_call_secs": 1,
      "agent_metadata": {
        "agent_id": "string",
        "branch_id": "string",
        "workflow_node_id": "string"
      },
      "message": "string",
      "multivoice_message": {
        "parts": [
          {
            "text": "string",
            "voice_label": "string",
            "time_in_call_secs": 1
          }
        ]
      },
      "tool_calls": [
        {
          "request_id": "string",
          "tool_name": "string",
          "params_as_json": "string",
          "tool_has_been_called": true,
          "type": "system",
          "tool_details": {
            "type": "webhook",
            "method": "string",
            "url": "string",
            "headers": {},
            "path_params": {},
            "query_params": {},
            "body": "string"
          }
        }
      ],
      "tool_results": [
        {
          "request_id": "string",
          "tool_name": "string",
          "result_value": "string",
          "is_error": true,
          "tool_has_been_called": true,
          "tool_latency_secs": 0,
          "error_type": "",
          "raw_error_message": "",
          "dynamic_variable_updates": [
            {
              "variable_name": "string",
              "old_value": "string",
              "new_value": "string",
              "updated_at": 1.1,
              "tool_name": "string",
              "tool_request_id": "string"
            }
          ],
          "type": "client"
        }
      ],
      "feedback": {
        "score": "like",
        "time_in_call_secs": 1
      },
      "llm_override": "string",
      "conversation_turn_metrics": {
        "metrics": {},
        "convai_asr_provider": "string"
      },
      "rag_retrieval_info": {
        "chunks": [
          {
            "document_id": "string",
            "chunk_id": "string",
            "vector_distance": 1.1
          }
        ],
        "embedding_model": "e5_mistral_7b_instruct",
        "retrieval_query": "string",
        "rag_latency_secs": 1.1
      },
      "llm_usage": {
        "model_usage": {}
      },
      "interrupted": false,
      "original_message": "string",
      "source_medium": "audio"
    }
  ],
  "success_condition": "string",
  "success_examples": [
    {
      "response": "string",
      "type": "string"
    }
  ],
  "failure_examples": [
    {
      "response": "string",
      "type": "string"
    }
  ],
  "id": "string",
  "name": "string",
  "tool_call_parameters": {
    "parameters": [
      {
        "eval": {
          "type": "string",
          "description": "string"
        },
        "path": "string"
      }
    ],
    "referenced_tool": {
      "id": "string",
      "type": "system"
    },
    "verify_absence": false
  },
  "check_any_tool_matches": true,
  "dynamic_variables": {},
  "type": "llm",
  "from_conversation_metadata": {
    "conversation_id": "string",
    "agent_id": "string",
    "workflow_node_id": "string",
    "original_agent_reply": [
      {
        "role": "user",
        "time_in_call_secs": 1,
        "agent_metadata": {
          "agent_id": "string",
          "branch_id": "string",
          "workflow_node_id": "string"
        },
        "message": "string",
        "multivoice_message": {
          "parts": [
            {
              "text": "string",
              "voice_label": "string",
              "time_in_call_secs": 1
            }
          ]
        },
        "tool_calls": [
          {
            "request_id": "string",
            "tool_name": "string",
            "params_as_json": "string",
            "tool_has_been_called": true,
            "type": "system",
            "tool_details": {
              "type": "webhook",
              "method": "string",
              "url": "string",
              "headers": {},
              "path_params": {},
              "query_params": {},
              "body": "string"
            }
          }
        ],
        "tool_results": [
          {
            "request_id": "string",
            "tool_name": "string",
            "result_value": "string",
            "is_error": true,
            "tool_has_been_called": true,
            "tool_latency_secs": 0,
            "error_type": "",
            "raw_error_message": "",
            "dynamic_variable_updates": [
              {
                "variable_name": "string",
                "old_value": "string",
                "new_value": "string",
                "updated_at": 1.1,
                "tool_name": "string",
                "tool_request_id": "string"
              }
            ],
            "type": "client"
          }
        ],
        "feedback": {
          "score": "like",
          "time_in_call_secs": 1
        },
        "llm_override": "string",
        "conversation_turn_metrics": {
          "metrics": {},
          "convai_asr_provider": "string"
        },
        "rag_retrieval_info": {
          "chunks": [
            {
              "document_id": "string",
              "chunk_id": "string",
              "vector_distance": 1.1
            }
          ],
          "embedding_model": "e5_mistral_7b_instruct",
          "retrieval_query": "string",
          "rag_latency_secs": 1.1
        },
        "llm_usage": {
          "model_usage": {}
        },
        "interrupted": false,
        "original_message": "string",
        "source_medium": "audio"
      }
    ]
  }
}

Gets an agent response test by ID.

Path parameters

test_idstringRequired

The id of a chat response test. This is returned on test creation.

Response

Successful Response

chat_historylist of objects

success_conditionstring

A prompt that evaluates whether the agent's response is successful. Should return True or False.

success_exampleslist of objects

Non-empty list of example responses that should be considered successful

failure_exampleslist of objects

Non-empty list of example responses that should be considered failures

idstring

namestring

tool_call_parametersobject or null

How to evaluate the agent’s tool call (if any). If empty, the tool call is not evaluated.

check_any_tool_matchesboolean or null

If set to True this test will pass if any tool call returned by the LLM matches the criteria. Otherwise it will fail if more than one tool is returned by the agent.

dynamic_variablesmap from strings to nullable strings or doubles or integers or booleans or null

Dynamic variables to replace in the agent config during testing

typeenum or null

Allowed values:

from_conversation_metadataobject or null

Metadata of a conversation this test was created from (if applicable).

Path parameters

Headers

Response

Errors