Implementation:Elevenlabs Elevenlabs python GetUnitTestResponseModel

Attribute	Value
Page Type	Implementation
Package	elevenlabs
Module	elevenlabs.types.get_unit_test_response_model
Class	GetUnitTestResponseModel
Base Class	UncheckedBaseModel
Source File	src/elevenlabs/types/get_unit_test_response_model.py
Auto-Generated	Yes (Fern API Definition)

Overview

Description

GetUnitTestResponseModel is a Pydantic-based data model representing the full response for an individual unit test. It encapsulates the complete test definition including chat history, success/failure evaluation criteria, tool call evaluation parameters, dynamic variables, and metadata about the test origin. This model extends the common unit test fields with id and name fields for identification.

Usage

This model is returned by API endpoints that retrieve a specific unit test by its ID. It provides the complete test definition, allowing consumers to inspect or execute the test. The test defines a chat scenario (via chat_history), a success condition prompt, example responses for success and failure, and optional tool call evaluation criteria.

Code Reference

Source Location

src/elevenlabs/types/get_unit_test_response_model.py

Class Signature

class GetUnitTestResponseModel(UncheckedBaseModel):
    ...

Import Statement

from elevenlabs.types.get_unit_test_response_model import GetUnitTestResponseModel

I/O Contract

Field Name	Type	Required	Default	Description
chat_history	List[ConversationHistoryTranscriptCommonModelOutput]	Yes	N/A	The chat history transcript that sets up the test scenario
success_condition	str	Yes	N/A	A prompt that evaluates whether the agent's response is successful. Should return True or False
success_examples	List[AgentSuccessfulResponseExample]	Yes	N/A	Non-empty list of example responses that should be considered successful
failure_examples	List[AgentFailureResponseExample]	Yes	N/A	Non-empty list of example responses that should be considered failures
tool_call_parameters	Optional[UnitTestToolCallEvaluationModelOutput]	No	None	How to evaluate the agent's tool call (if any). If empty, the tool call is not evaluated
check_any_tool_matches	Optional[bool]	No	None	If True, the test passes if any tool call matches the criteria. Otherwise fails if more than one tool is returned
dynamic_variables	Optional[Dict[str, Optional[GetUnitTestResponseModelDynamicVariablesValue]]]	No	None	Dynamic variables to replace in the agent config during testing
type	Optional[UnitTestCommonModelType]	No	None	The type classification of the unit test
from_conversation_metadata	Optional[TestFromConversationMetadataOutput]	No	None	Metadata of a conversation this test was created from (if applicable)
id	str	Yes	N/A	Unique identifier of the unit test
name	str	Yes	N/A	Name of the unit test

Usage Examples

Inspecting a Unit Test

from elevenlabs.types.get_unit_test_response_model import GetUnitTestResponseModel

# Assuming `test` is a GetUnitTestResponseModel returned by the API
print(f"Test: {test.name} (ID: {test.id})")
print(f"Success condition: {test.success_condition}")
print(f"Chat history steps: {len(test.chat_history)}")
print(f"Success examples: {len(test.success_examples)}")
print(f"Failure examples: {len(test.failure_examples)}")

Checking Tool Call and Dynamic Variable Configuration

# Check if tool call evaluation is configured
if test.tool_call_parameters:
    print("Tool call evaluation is configured")
    if test.check_any_tool_matches:
        print("  Mode: any tool match accepted")
    else:
        print("  Mode: single tool match required")

# Check dynamic variables
if test.dynamic_variables:
    for var_name, var_value in test.dynamic_variables.items():
        print(f"  Variable '{var_name}': {var_value}")

# Check if test was created from a conversation
if test.from_conversation_metadata:
    print(f"Created from conversation: {test.from_conversation_metadata}")

Related Pages

• Elevenlabs_Elevenlabs_python_UnitTestCommonModel
• Elevenlabs_Elevenlabs_python_UnitTestSummaryResponseModel
• Elevenlabs_Elevenlabs_python_UnitTestToolCallEvaluationModelInput
• Elevenlabs_Elevenlabs_python_UnitTestToolCallParameterEval