Get test

GET

/v1/convai/agent-testing/:test_id

GET

/v1/convai/agent-testing/:test_id

1 from elevenlabs import ElevenLabs
2 
3 client = ElevenLabs(
4     api_key="YOUR_API_KEY",
5 )
6 client.get_agent_response_test_route(
7     test_id="TeaqRRdTcIfIu2i7BYfT",
8 )

Try it

1 {
2   "chat_history": [
3     {
4       "role": "user",
5       "time_in_call_secs": 1,
6       "message": "string",
7       "tool_calls": [
8         {
9           "request_id": "string",
10           "tool_name": "string",
11           "params_as_json": "string",
12           "tool_has_been_called": true,
13           "type": "system",
14           "tool_details": {
15             "type": "webhook",
16             "method": "string",
17             "url": "string",
18             "headers": {},
19             "path_params": {},
20             "query_params": {},
21             "body": "string"
22           }
23         }
24       ],
25       "tool_results": [
26         {
27           "request_id": "string",
28           "tool_name": "string",
29           "result_value": "string",
30           "is_error": true,
31           "tool_has_been_called": true,
32           "tool_latency_secs": 0,
33           "dynamic_variable_updates": [
34             {
35               "variable_name": "string",
36               "old_value": "string",
37               "new_value": "string",
38               "updated_at": 1.1,
39               "tool_name": "string",
40               "tool_request_id": "string"
41             }
42           ],
43           "type": "client"
44         }
45       ],
46       "feedback": {
47         "score": "like",
48         "time_in_call_secs": 1
49       },
50       "llm_override": "string",
51       "conversation_turn_metrics": {
52         "metrics": {}
53       },
54       "rag_retrieval_info": {
55         "chunks": [
56           {
57             "document_id": "string",
58             "chunk_id": "string",
59             "vector_distance": 1.1
60           }
61         ],
62         "embedding_model": "e5_mistral_7b_instruct",
63         "retrieval_query": "string",
64         "rag_latency_secs": 1.1
65       },
66       "llm_usage": {
67         "model_usage": {}
68       },
69       "interrupted": false,
70       "original_message": "string",
71       "source_medium": "audio"
72     }
73   ],
74   "success_condition": "string",
75   "success_examples": [
76     {
77       "response": "string",
78       "type": "string"
79     }
80   ],
81   "failure_examples": [
82     {
83       "response": "string",
84       "type": "string"
85     }
86   ],
87   "id": "string",
88   "name": "string",
89   "tool_call_parameters": {
90     "referenced_tool": {
91       "id": "string",
92       "type": "system"
93     },
94     "parameters": [
95       {
96         "eval": {
97           "type": "string",
98           "description": "string"
99         },
100         "path": "string"
101       }
102     ]
103   },
104   "dynamic_variables": {}
105 }

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.

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

Get test

Path parameters

Headers

Response

Errors