> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# 创建智能体响应测试

POST https://api.elevenlabs.io/v1/convai/agent-testing/create
Content-Type: application/json

创建新的智能体响应测试。

Reference: https://elevenlabs.io/docs/eleven-agents/api-reference/tests/create

## Servers

- `https://api.elevenlabs.io` (Production, default)
- `https://api.us.elevenlabs.io` (Production US)
- `https://api.eu.residency.elevenlabs.io` (Production EU)
- `https://api.in.residency.elevenlabs.io` (Production India)
- `https://api.sg.residency.elevenlabs.io` (Production Singapore)

## Request

### Body (application/json)

This endpoint expects a TestsCreateRequestBody.

- `TestsCreateRequestBody`
  - `type`: `llm`
    - `name` (string, required)
    - `chat_history` (list of ConversationHistoryTranscriptCommonModelInput, optional)
    - `conversation_initiation_source` (enum, optional, default: unknown) — 模拟测试，使对话看似从此渠道发起。
      - Allowed values: `unknown`, `android_sdk`, `node_js_sdk`, `react_native_sdk`, `react_sdk`, `js_sdk`, `python_sdk`, `widget`, `sip_trunk`, `twilio`, `exotel`, `genesys`, `avaya`, `audiocodes`, `swift_sdk`, `whatsapp`, `twilio_sms`, `flutter_sdk`, `zendesk_integration`, `slack_integration`, `telegram_integration`, `intercom_integration`, `freshdesk_integration`, `salesforce_integration`, `template_preview`, `genesys_bot_connector`, `subagent_tool`
    - `dynamic_variables` (map from string to any, optional) — 测试期间要在智能体配置中替换的动态变量
    - `environment` (string, optional) — 运行此测试时，用于解析环境特定变量值（URL、标头、身份验证连接）的环境。未提供时默认为 'production'。对于模拟测试，设置后 simulation_environment 优先。
    - `failure_examples` (list of AgentFailureResponseExample, optional) — 应视为失败的示例回复非空列表
    - `from_conversation_metadata` (TestFromConversationMetadataInput, optional) — 创建此测试所依据的对话元数据（如适用）。
    - `parent_folder_id` (string, optional) — 父文件夹的 ID。未提供时，测试将在根目录创建。
    - `success_condition` (string, optional, default: ) — 用于评估智能体回复是否成功的提示词。应返回 True 或 False。
    - `success_examples` (list of AgentSuccessfulResponseExample, optional) — 应视为成功的示例回复非空列表
  - `type`: `tool`
    - `name` (string, required)
    - `chat_history` (list of ConversationHistoryTranscriptCommonModelInput, optional)
    - `check_any_tool_matches` (boolean, optional) — 设为 True 时，只要 LLM 返回的任一工具调用符合条件，此测试即通过。否则，如果智能体返回多个工具，测试将失败。
    - `conversation_initiation_source` (enum, optional, default: unknown) — 模拟测试，使对话看似从此渠道发起。
      - Allowed values: `unknown`, `android_sdk`, `node_js_sdk`, `react_native_sdk`, `react_sdk`, `js_sdk`, `python_sdk`, `widget`, `sip_trunk`, `twilio`, `exotel`, `genesys`, `avaya`, `audiocodes`, `swift_sdk`, `whatsapp`, `twilio_sms`, `flutter_sdk`, `zendesk_integration`, `slack_integration`, `telegram_integration`, `intercom_integration`, `freshdesk_integration`, `salesforce_integration`, `template_preview`, `genesys_bot_connector`, `subagent_tool`
    - `dynamic_variables` (map from string to any, optional) — 测试期间要在智能体配置中替换的动态变量
    - `environment` (string, optional) — 运行此测试时，用于解析环境特定变量值（URL、标头、身份验证连接）的环境。未提供时默认为 'production'。对于模拟测试，设置后 simulation_environment 优先。
    - `from_conversation_metadata` (TestFromConversationMetadataInput, optional) — 创建此测试所依据的对话元数据（如适用）。
    - `parent_folder_id` (string, optional) — 父文件夹的 ID。未提供时，测试将在根目录创建。
    - `tool_call_parameters` (UnitTestToolCallEvaluationModelInput, optional) — 如何评估智能体的工具调用（如有）。为空时，不评估工具调用。
  - `type`: `simulation`
    - `name` (string, required)
    - `chat_history` (list of ConversationHistoryTranscriptCommonModelInput, optional)
    - `conversation_initiation_source` (enum, optional, default: unknown) — 模拟测试，使对话看似从此渠道发起。
      - Allowed values: `unknown`, `android_sdk`, `node_js_sdk`, `react_native_sdk`, `react_sdk`, `js_sdk`, `python_sdk`, `widget`, `sip_trunk`, `twilio`, `exotel`, `genesys`, `avaya`, `audiocodes`, `swift_sdk`, `whatsapp`, `twilio_sms`, `flutter_sdk`, `zendesk_integration`, `slack_integration`, `telegram_integration`, `intercom_integration`, `freshdesk_integration`, `salesforce_integration`, `template_preview`, `genesys_bot_connector`, `subagent_tool`
    - `dynamic_variables` (map from string to any, optional) — 测试期间要在智能体配置中替换的动态变量
    - `environment` (string, optional) — 运行此测试时，用于解析环境特定变量值（URL、标头、身份验证连接）的环境。未提供时默认为 'production'。对于模拟测试，设置后 simulation_environment 优先。
    - `evaluation_model` (enum, optional) — 用于评估模拟结果的 LLM 模型。
      - Allowed values: `gpt-4o-mini`, `gpt-4o`, `gpt-4`, `gpt-4-turbo`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-5`, `gpt-5.1`, `gpt-5.2`, `gpt-5.2-chat-latest`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-6-astra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-6.1-sol`, `gpt-5-mini`, `gpt-5-nano`, `gpt-3.5-turbo`, `gemini-1.5-pro`, `gemini-1.5-flash`, `gemini-2.0-flash`, `gemini-2.0-flash-lite`, `gemini-2.5-flash-lite`, `gemini-2.5-flash`, `gemini-3-pro-preview`, `gemini-3-flash-preview`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-flash-lite`, `gemini-3.5-flash`, `gemini-3.5-flash-lite`, `gemini-3.6-flash`, `gemini-3.7-flash`, `gemini-3.8-flash`, `gemini-4-argon`, `claude-sonnet-4-5`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-opus-5-5`, `claude-sonnet-4-6`, `claude-sonnet-5`, `claude-sonnet-5-5`, `claude-sonnet-4`, `claude-haiku-4-5`, `claude-haiku-5-5`, `claude-3-7-sonnet`, `claude-3-5-sonnet`, `claude-3-5-sonnet-v1`, `claude-3-haiku`, `grok-beta`, `custom-llm`, `qwen3-4b`, `qwen3-30b-a3b`, `qwen36-35b-a3b`, `qwen35-397b-a17b`, `gpt-oss-20b`, `gpt-oss-120b`, `glm-45-air-fp8`, `glm-52`, `deepseek-v41-flash`, `nemotron-35-super-vl-nvfp4`, `gemini-2.5-flash-preview-09-2025`, `gemini-2.5-flash-lite-preview-09-2025`, `gemini-2.5-flash-preview-05-20`, `gemini-2.5-flash-preview-04-17`, `gemini-2.5-flash-lite-preview-06-17`, `gemini-2.0-flash-lite-001`, `gemini-2.0-flash-001`, `gemini-1.5-flash-002`, `gemini-1.5-flash-001`, `gemini-1.5-pro-002`, `gemini-1.5-pro-001`, `claude-sonnet-4@20250514`, `claude-sonnet-4-5@20250929`, `claude-haiku-4-5@20251001`, `claude-3-7-sonnet@20250219`, `claude-3-5-sonnet@20240620`, `claude-3-5-sonnet-v2@20241022`, `claude-3-haiku@20240307`, `gpt-5-2025-08-07`, `gpt-5.1-2025-11-13`, `gpt-5.2-2025-12-11`, `gpt-5.4-2026-03-05`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.5-2026-04-23`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `gpt-4o-mini-2024-07-18`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-2024-05-13`, `gpt-4-0613`, `gpt-4-0314`, `gpt-4-turbo-2024-04-09`, `gpt-3.5-turbo-0125`, `gpt-3.5-turbo-1106`, `watt-tool-8b`, `watt-tool-70b`
    - `from_conversation_metadata` (TestFromConversationMetadataInput, optional) — 创建此测试所依据的对话元数据（如适用）。
    - `parent_folder_id` (string, optional) — 父文件夹的 ID。未提供时，测试将在根目录创建。
    - `simulated_user_model` (enum, optional) — 用于模拟用户的 LLM 模型。
      - Allowed values: `gpt-4o-mini`, `gpt-4o`, `gpt-4`, `gpt-4-turbo`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-5`, `gpt-5.1`, `gpt-5.2`, `gpt-5.2-chat-latest`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.5`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-6-astra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-6.1-sol`, `gpt-5-mini`, `gpt-5-nano`, `gpt-3.5-turbo`, `gemini-1.5-pro`, `gemini-1.5-flash`, `gemini-2.0-flash`, `gemini-2.0-flash-lite`, `gemini-2.5-flash-lite`, `gemini-2.5-flash`, `gemini-3-pro-preview`, `gemini-3-flash-preview`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite-preview`, `gemini-3.1-flash-lite`, `gemini-3.5-flash`, `gemini-3.5-flash-lite`, `gemini-3.6-flash`, `gemini-3.7-flash`, `gemini-3.8-flash`, `gemini-4-argon`, `claude-sonnet-4-5`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-opus-5-5`, `claude-sonnet-4-6`, `claude-sonnet-5`, `claude-sonnet-5-5`, `claude-sonnet-4`, `claude-haiku-4-5`, `claude-haiku-5-5`, `claude-3-7-sonnet`, `claude-3-5-sonnet`, `claude-3-5-sonnet-v1`, `claude-3-haiku`, `grok-beta`, `custom-llm`, `qwen3-4b`, `qwen3-30b-a3b`, `qwen36-35b-a3b`, `qwen35-397b-a17b`, `gpt-oss-20b`, `gpt-oss-120b`, `glm-45-air-fp8`, `glm-52`, `deepseek-v41-flash`, `nemotron-35-super-vl-nvfp4`, `gemini-2.5-flash-preview-09-2025`, `gemini-2.5-flash-lite-preview-09-2025`, `gemini-2.5-flash-preview-05-20`, `gemini-2.5-flash-preview-04-17`, `gemini-2.5-flash-lite-preview-06-17`, `gemini-2.0-flash-lite-001`, `gemini-2.0-flash-001`, `gemini-1.5-flash-002`, `gemini-1.5-flash-001`, `gemini-1.5-pro-002`, `gemini-1.5-pro-001`, `claude-sonnet-4@20250514`, `claude-sonnet-4-5@20250929`, `claude-haiku-4-5@20251001`, `claude-3-7-sonnet@20250219`, `claude-3-5-sonnet@20240620`, `claude-3-5-sonnet-v2@20241022`, `claude-3-haiku@20240307`, `gpt-5-2025-08-07`, `gpt-5.1-2025-11-13`, `gpt-5.2-2025-12-11`, `gpt-5.4-2026-03-05`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.5-2026-04-23`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `gpt-4o-mini-2024-07-18`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-2024-05-13`, `gpt-4-0613`, `gpt-4-0314`, `gpt-4-turbo-2024-04-09`, `gpt-3.5-turbo-0125`, `gpt-3.5-turbo-1106`, `watt-tool-8b`, `watt-tool-70b`
    - `simulation_environment` (string, optional) — 运行此模拟测试时使用的环境。未提供时默认为 'production'。
    - `simulation_max_turns` (integer, optional, default: 5) — 模拟测试的最大对话轮数。
    - `simulation_scenario` (string, optional, default: ) — 模拟测试的场景和用户角色说明。
    - `success_conditions` (list of string, optional) — 用于评估模拟是否成功的提示词列表。如提供，将评估所有条件并合并为最终结果。数量上限为最大评估条件数。
    - `tool_mock_config` (SimulationToolMockBehaviorConfig, optional) — Configuration for which tools to mock and fallback behavior.
    - `tool_mock_overrides` (map from string to list of ToolResponseMockConfigInput, optional) — 测试专用响应模拟，以工具 ID 为键。优先于工具共享模拟应用，且仅在此测试内生效。仅对已模拟的工具有效（参见 tool_mock_config）。
    - `success_condition` (string, optional, deprecated) — 已弃用的旧版单一成功条件。请改用 success_conditions。success_condition 或 success_conditions 至少需要提供一个。

## Response

### 200

成功响应

- `id` (string, required)

## Errors

### 422 Tests Create Request Unprocessable Entity Error

验证错误。

- `detail` (list of ValidationError, optional)

## Types

### ConversationHistoryTranscriptCommonModelInput

- `role` (enum, required)
  - Allowed values: `user`, `agent`
- `time_in_call_secs` (integer, required)
- `agent_metadata` (AgentMetadata, optional)
- `message` (string, optional)
- `multivoice_message` (ConversationHistoryMultivoiceMessageModel, optional) — 表示来自多音色智能体的消息。
- `tool_calls` (list of ConversationHistoryTranscriptToolCallCommonModelInput, optional)
- `tool_results` (list of ConversationHistoryTranscriptCommonModelInputToolResultsItem, optional)
- `feedback` (UserFeedback, optional)
- `llm_override` (string, optional)
- `producing_llm` (string, optional)
- `conversation_turn_metrics` (ConversationTurnMetrics, optional)
- `rag_retrieval_info` (RagRetrievalInfo, optional)
- `llm_usage` (LlmUsageInput, optional)
- `interrupted` (boolean, optional, default: false)
- `ignored_as_backchannel` (boolean, optional, default: false)
- `platform_event` (enum, optional)
  - Allowed values: `user_turn_timeout`, `skip_turn_wait_elapsed`
- `original_message` (string, optional)
- `reasoning` (list of ConversationReasoningModel, optional)
- `source_medium` (enum, optional)
  - Allowed values: `audio`, `dtmf`, `text`, `image`, `file`
- `source_event_id` (integer, optional)
- `used_static_kb_document_ids` (list of string, optional)
- `user_identifier` (string, optional)
- `id` (string, optional)
- `triggered_guardrails` (list of TriggeredGuardrailCommonModel, optional)

### AgentFailureResponseExample

- `response` (string, required)
- `type` ("failure", required)

### TestFromConversationMetadataInput

- `conversation_id` (string, required)
- `agent_id` (string, required)
- `branch_id` (string, optional)
- `workflow_node_id` (string, optional)
- `original_agent_reply` (list of ConversationHistoryTranscriptCommonModelInput, optional, default: [])

### AgentSuccessfulResponseExample

- `response` (string, required)
- `type` ("success", required)

### UnitTestToolCallEvaluationModelInput

- `parameters` (list of UnitTestToolCallParameter, optional) — 要评估的智能体工具调用参数。为空时，不评估工具调用参数。
- `referenced_tool` (ReferencedToolCommonModel, optional) — 用于评估通话的工具。
- `verify_absence` (boolean, optional, default: false) — 是否验证未调用该工具。
- `workflow_node_transition` (UnitTestWorkflowNodeTransitionEvaluationNodeId, optional) — Configuration for testing workflow node transitions. When set, the test will verify the agent transitions to the specified workflow node.

### SimulationToolMockBehaviorConfig

模拟／预览端配置：工具通过 ID 标识，运行时解析为名称。

- `mocking_strategy` (enum, optional, default: none) — 要模拟哪些工具：'all' 模拟所有可模拟工具，'selected' 仅模拟 mocked_tool_names/mocked_tool_ids 中的工具，'none' 禁用模拟。
  - Allowed values: `all`, `selected`, `none`
- `fallback_strategy` (enum, optional, default: raise_error) — Behavior when no mock matches a tool call.
  - Allowed values: `call_real_tool`, `raise_error`
- `mocked_tool_ids` (list of string, optional) — 要模拟的工具 ID。在传递给编排器前会解析为工具名称。

### ToolResponseMockConfigInput

- `mock_result` (string, required) — 此模拟处于启用状态时，LLM 看到的返回值。
- `parameter_conditions` (list of UnitTestToolCallParameter, optional) — 如果列表为空，模拟将始终启用。
- `is_error` (boolean, optional, default: false) — 如果为 true，模拟结果将作为工具错误而非成功结果提供给 LLM。

### ValidationError

- `loc` (list of ValidationErrorLocItem, required)
- `msg` (string, required)
- `type` (string, required)

### AgentMetadata

- `agent_id` (string, required)
- `branch_id` (string, optional)
- `workflow_node_id` (string, optional)
- `version_id` (string, optional)

### ConversationHistoryMultivoiceMessageModel

表示来自多音色智能体的消息。

- `parts` (list of ConversationHistoryMultivoiceMessagePartModel, required)

### ConversationHistoryTranscriptToolCallCommonModelInput

- `request_id` (string, required)
- `tool_name` (string, required)
- `params_as_json` (string, required)
- `tool_has_been_called` (boolean, required)
- `type` (enum, optional)
  - Allowed values: `system`, `webhook`, `client`, `mcp`, `workflow`, `api_integration_webhook`, `smb`
- `tool_id` (string, optional) — 所调用工具的 ID。对于没有 ID 的工具（如系统工具），不会设置此项。
- `tool_details` (ConversationHistoryTranscriptToolCallCommonModelInputToolDetails, optional)

### ConversationHistoryTranscriptCommonModelInputToolResultsItem

- Conversation History Transcript Other Tools Result Common Model: ConversationHistoryTranscriptOtherToolsResultCommonModel
- Conversation History Transcript System Tool Result Common Model Input: ConversationHistoryTranscriptSystemToolResultCommonModelInput
- Conversation History Transcript API Integration Webhook Tools Result Common Model Input: ConversationHistoryTranscriptApiIntegrationWebhookToolsResultCommonModelInput
- Conversation History Transcript Workflow Tools Result Common Model Input: ConversationHistoryTranscriptWorkflowToolsResultCommonModelInput

### UserFeedback

- `score` (enum, required)
  - Allowed values: `like`, `dislike`
- `time_in_call_secs` (integer, required)

### ConversationTurnMetrics

- `metrics` (map from string to MetricRecord, optional)
- `convai_asr_provider` (string, optional)
- `convai_tts_model` (string, optional)
- `convai_tts_cascade` (string, optional)
- `voice_id` (string, optional)

### RagRetrievalInfo

- `chunks` (list of RagChunkMetadata, required)
- `embedding_model` (enum, required, default: e5_mistral_7b_instruct)
  - Allowed values: `e5_mistral_7b_instruct`, `multilingual_e5_large_instruct`
- `retrieval_query` (string, required)
- `rag_latency_secs` (double, required)
- `used_chunk_ids` (list of string, optional)

### LlmUsageInput

- `model_usage` (map from string to LlmInputOutputTokensUsage, optional)

### ConversationReasoningModel

- `summary` (string, optional)
- `provider_redact` (boolean, optional, default: false)

### TriggeredGuardrailCommonModel

- `guardrail_type` (enum, required)
  - Allowed values: `custom`, `prompt_injection`, `self_harm_intent`, `violence_graphic`, `sexual`, `violence`, `harassment`, `sexual_minors`, `self_harm`, `self_harm_instructions`, `harassment_threatening`, `hate`, `hate_threatening`, `profanity`, `religion_or_politics`, `medical_and_legal`, `guardrail`
- `guardrail_name` (string, optional)

### UnitTestToolCallParameter

- `eval` (UnitTestToolCallParameterEval, required)
- `path` (string, required)

### ReferencedToolCommonModel

用于单元测试评估的工具引用。

- `id` (string, required) — 工具的 ID
- `type` (enum, required) — 工具类型
  - Allowed values: `system`, `webhook`, `client`, `workflow`, `api_integration_webhook`, `mcp`, `code`

### UnitTestWorkflowNodeTransitionEvaluationNodeId

- `agent_id` (string, required) — 工作流程包含目标节点的智能体 ID。
- `target_node_id` (string, required) — 智能体应转移到的 workflow 节点 ID。
- `type` ("node_id", optional)

### ValidationErrorLocItem

- string
- integer

### ConversationHistoryMultivoiceMessagePartModel

表示多音色消息中的单个音色部分。

- `text` (string, required)
- `voice_label` (string, optional)
- `time_in_call_secs` (integer, optional)

### ConversationHistoryTranscriptToolCallCommonModelInputToolDetails

- `type`: `api_integration_webhook`
  - `webhook_details` (ConversationHistoryTranscriptToolCallWebhookDetails, required)
  - `credential_id` (string, optional, default: )
  - `integration_connection_id` (string, optional, default: )
  - `integration_id` (string, optional, default: )
- `type`: `client`
  - `parameters` (string, required)
- `type`: `mcp`
  - `approval_policy` (string, required)
  - `integration_type` (string, required)
  - `mcp_server_id` (string, required)
  - `mcp_server_name` (string, required)
  - `mcp_tool_description` (string, optional, default: )
  - `mcp_tool_name` (string, optional, default: )
  - `parameters` (map from string to string, optional)
  - `requires_approval` (boolean, optional, default: false)
- `type`: `webhook`
  - `method` (string, required)
  - `url` (string, required)
  - `body` (string, optional)
  - `headers` (map from string to string, optional)
  - `path_params` (map from string to string, optional)
  - `query_params` (map from string to string, optional)

### ConversationHistoryTranscriptOtherToolsResultCommonModel

- `request_id` (string, required)
- `tool_name` (string, required)
- `result_value` (string, required)
- `is_error` (boolean, required)
- `tool_has_been_called` (boolean, required)
- `is_blocked` (boolean, optional, default: false)
- `tool_latency_secs` (double, optional, default: 0)
- `error_type` (string, optional, default: )
- `raw_error_message` (string, optional, default: )
- `dynamic_variable_updates` (list of DynamicVariableUpdateCommonModel, optional)
- `type` (enum, optional)
  - Allowed values: `client`, `webhook`, `mcp`, `code`

### ConversationHistoryTranscriptSystemToolResultCommonModelInput

- `request_id` (string, required)
- `tool_name` (string, required)
- `result_value` (string, required)
- `is_error` (boolean, required)
- `tool_has_been_called` (boolean, required)
- `type` ("system", required)
- `is_blocked` (boolean, optional, default: false)
- `tool_latency_secs` (double, optional, default: 0)
- `error_type` (string, optional, default: )
- `raw_error_message` (string, optional, default: )
- `dynamic_variable_updates` (list of DynamicVariableUpdateCommonModel, optional)
- `result` (ConversationHistoryTranscriptSystemToolResultCommonModelInputResult, optional)

### ConversationHistoryTranscriptApiIntegrationWebhookToolsResultCommonModelInput

- `request_id` (string, required)
- `tool_name` (string, required)
- `result_value` (string, required)
- `is_error` (boolean, required)
- `tool_has_been_called` (boolean, required)
- `type` ("api_integration_webhook", required)
- `is_blocked` (boolean, optional, default: false)
- `tool_latency_secs` (double, optional, default: 0)
- `error_type` (string, optional, default: )
- `raw_error_message` (string, optional, default: )
- `dynamic_variable_updates` (list of DynamicVariableUpdateCommonModel, optional)
- `integration_id` (string, optional, default: )
- `credential_id` (string, optional, default: )
- `integration_connection_id` (string, optional, default: )

### ConversationHistoryTranscriptWorkflowToolsResultCommonModelInput

- `request_id` (string, required)
- `tool_name` (string, required)
- `result_value` (string, required)
- `is_error` (boolean, required)
- `tool_has_been_called` (boolean, required)
- `type` ("workflow", required)
- `is_blocked` (boolean, optional, default: false)
- `tool_latency_secs` (double, optional, default: 0)
- `error_type` (string, optional, default: )
- `raw_error_message` (string, optional, default: )
- `dynamic_variable_updates` (list of DynamicVariableUpdateCommonModel, optional)
- `result` (WorkflowToolResponseModelInput, optional) — workflow 工具响应的通用模型。

### MetricRecord

- `elapsed_time` (double, required)

### RagChunkMetadata

- `document_id` (string, required)
- `chunk_id` (string, required)
- `vector_distance` (double, required)

### LlmInputOutputTokensUsage

- `input` (LlmTokensCategoryUsage, optional)
- `input_cache_read` (LlmTokensCategoryUsage, optional)
- `input_cache_write` (LlmTokensCategoryUsage, optional)
- `output_total` (LlmTokensCategoryUsage, optional)

### UnitTestToolCallParameterEval

- `type`: `anything`
- `type`: `exact`
  - `expected_value` (string, required) — 参数必须匹配的精确字符串值。
- `type`: `llm`
  - `description` (string, required) — 用于测试的评估策略说明。
- `type`: `regex`
  - `pattern` (string, required) — 用于匹配智能体回复的正则表达式模式。

### ConversationHistoryTranscriptToolCallWebhookDetails

- `method` (string, required)
- `url` (string, required)
- `type` ("webhook", optional)
- `headers` (map from string to string, optional)
- `path_params` (map from string to string, optional)
- `query_params` (map from string to string, optional)
- `body` (string, optional)

### DynamicVariableUpdateCommonModel

跟踪工具执行期间发生的动态变量更新。

- `variable_name` (string, required)
- `new_value` (string, required)
- `updated_at` (double, required)
- `tool_name` (string, required)
- `tool_request_id` (string, required)
- `old_value` (string, optional)

### ConversationHistoryTranscriptSystemToolResultCommonModelInputResult

- `result_type`: `dummy`
- `result_type`: `end_call_success`
  - `message` (string, optional)
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `end_procedure_error`
  - `message` (string, required)
  - `status` (enum, required)
    - Allowed values: `not_found`, `invalid_id`
  - `procedure_id` (string, optional)
- `result_type`: `end_procedure_success`
  - `procedure_id` (string, required)
  - `procedure_name` (string, required)
  - `message` (string, optional, default: )
  - `status` ("success", optional)
- `result_type`: `knowledge_base_rag_success`
  - `chunk_count` (integer, optional, default: 0) — 检索到的相关块数量
  - `chunks` (list of KnowledgeBaseRagChunkModel, optional) — 检索到的分块；仅在 rag-result-in-tool-result 模式下填充。
  - `message` (string, optional, default: Referenced knowledge base.) — 供 LLM 使用的搜索结果人类可读状态
  - `status` (enum, optional, default: success)
    - Allowed values: `success`, `no_documents`, `no_results`
- `result_type`: `knowledge_base_success`
  - `chunk_count` (integer, optional, default: 0)
  - `message` (string, optional, default: Referenced knowledge base.)
  - `status` (enum, optional, default: success)
    - Allowed values: `success`, `no_matching_documents`, `no_results`
- `result_type`: `language_detection_success`
  - `language` (string, optional)
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `play_dtmf_error`
  - `error` (string, required)
  - `details` (string, optional)
  - `status` ("error", optional)
- `result_type`: `play_dtmf_success`
  - `dtmf_tones` (string, required)
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `skip_turn_success`
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `start_procedure_error`
  - `message` (string, required)
  - `status` (enum, required)
    - Allowed values: `not_found`, `invalid_name`, `already_active`
  - `procedure_id` (string, optional)
- `result_type`: `start_procedure_success`
  - `procedure_id` (string, required)
  - `procedure_name` (string, required)
  - `message` (string, optional, default: Procedure is now started. Follow its instructions from the <active-procedures> section of your system prompt.)
  - `procedure_entry_workflow_node` (string, optional)
  - `procedure_return_workflow_node` (string, optional)
  - `status` ("success", optional)
- `result_type`: `testing_tool_result`
  - `reason` (string, optional, default: Skipping tool call in test mode)
  - `status` ("success", optional)
  - `to_agent` (string, optional)
  - `to_node` (string, optional)
- `result_type`: `transfer_to_agent_error`
  - `error` (string, required)
  - `from_agent` (string, required)
  - `status` ("error", optional)
- `result_type`: `transfer_to_agent_success`
  - `condition` (string, required)
  - `from_agent` (string, required)
  - `to_agent` (string, required)
  - `branch_info` (TransferToAgentToolResultSuccessModelInputBranchInfo, optional)
  - `delay_ms` (integer, optional, default: 0)
  - `enable_transferred_agent_first_message` (boolean, optional, default: false)
  - `preserve_client_tts_overrides` (boolean, optional, default: false)
  - `preserve_voice_settings` (boolean, optional, default: false)
  - `status` ("success", optional)
  - `to_node` (string, optional)
  - `transfer_message` (string, optional)
- `result_type`: `transfer_to_number_amazon_connect_success`
  - `client_message` (string, optional) — 将会话交还给 Amazon Connect 前向来电者播放的消息。
  - `note` (string, optional) — 当智能体复述无效选项且已使用唯一配置的选项时设置。
  - `reason` (string, optional) — 智能体升级的原因，会随 Escalate 结果发送至 Amazon Connect。
  - `status` ("success", optional)
- `result_type`: `transfer_to_number_error`
  - `error` (string, required)
  - `details` (string, optional)
  - `status` ("error", optional)
- `result_type`: `transfer_to_number_exotel_success`
  - `transfer_number` (string, required)
  - `agent_message` (string, optional)
  - `note` (string, optional)
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `transfer_to_number_sip_success`
  - `transfer_number` (string, required)
  - `note` (string, optional)
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `transfer_to_number_twilio_success`
  - `agent_message` (string, required)
  - `conference_name` (string, required)
  - `transfer_number` (string, required)
  - `client_message` (string, optional)
  - `note` (string, optional)
  - `post_dial_digits` (string, optional)
  - `reason` (string, optional)
  - `status` ("success", optional)
- `result_type`: `voicemail_detection_success`
  - `reason` (string, optional)
  - `status` ("success", optional)
  - `voicemail_message` (string, optional)

### WorkflowToolResponseModelInput

workflow 工具响应的通用模型。

- `steps` (list of WorkflowToolResponseModelInputStepsItem, optional)

### LlmTokensCategoryUsage

- `tokens` (integer, optional, default: 0)
- `price` (double, optional, default: 0)

### KnowledgeBaseRagChunkModel

- `chunk_id` (string, required)
- `document_id` (string, required)
- `content` (string, required)

### TransferToAgentToolResultSuccessModelInputBranchInfo

- `branch_reason`: `configured`
  - `branch_id` (string, required)
- `branch_reason`: `defaulting_to_main`
  - `branch_id` (string, required)
- `branch_reason`: `traffic_split`
  - `branch_id` (string, required)
  - `traffic_percentage` (double, required)

### WorkflowToolResponseModelInputStepsItem

- `type`: `edge`
  - `edge_id` (string, required)
  - `step_latency_secs` (double, required)
  - `target_node_id` (string, required)
- `type`: `max_iterations_exceeded`
  - `max_iterations` (integer, required)
  - `step_latency_secs` (double, required)
- `type`: `nested_tools`
  - `is_successful` (boolean, required)
  - `node_id` (string, required)
  - `requests` (list of ConversationHistoryTranscriptToolCallCommonModelInput, required)
  - `results` (list of WorkflowToolNestedToolsStepModelInputResultsItem, required)
  - `step_latency_secs` (double, required)

### WorkflowToolNestedToolsStepModelInputResultsItem

- Conversation History Transcript Other Tools Result Common Model: ConversationHistoryTranscriptOtherToolsResultCommonModel
- Conversation History Transcript System Tool Result Common Model Input: ConversationHistoryTranscriptSystemToolResultCommonModelInput
- Conversation History Transcript API Integration Webhook Tools Result Common Model Input: ConversationHistoryTranscriptApiIntegrationWebhookToolsResultCommonModelInput
- Conversation History Transcript Workflow Tools Result Common Model Input: ConversationHistoryTranscriptWorkflowToolsResultCommonModelInput

## Examples

**Request**

```json
{
  "type": "llm",
  "name": "name"
}
```

**Response**

```json
{
  "id": "id"
}
```

**SDK Code**

```python
import requests

url = "https://api.elevenlabs.io/v1/convai/agent-testing/create"

payload = {
    "type": "llm",
    "name": "name"
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.elevenlabs.io/v1/convai/agent-testing/create';
const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: '{"type":"llm","name":"name"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.elevenlabs.io/v1/convai/agent-testing/create"

	payload := strings.NewReader("{\n  \"type\": \"llm\",\n  \"name\": \"name\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.elevenlabs.io/v1/convai/agent-testing/create")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"type\": \"llm\",\n  \"name\": \"name\"\n}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.elevenlabs.io/v1/convai/agent-testing/create")
  .header("Content-Type", "application/json")
  .body("{\n  \"type\": \"llm\",\n  \"name\": \"name\"\n}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.elevenlabs.io/v1/convai/agent-testing/create', [
  'body' => '{
  "type": "llm",
  "name": "name"
}',
  'headers' => [
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.elevenlabs.io/v1/convai/agent-testing/create");
var request = new RestRequest(Method.POST);
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"type\": \"llm\",\n  \"name\": \"name\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = ["Content-Type": "application/json"]
let parameters = [
  "type": "llm",
  "name": "name"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.elevenlabs.io/v1/convai/agent-testing/create")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```