AI Agent
Authorization
Signed mode: every request is signed with your App Key/Secret. Header set:
| Name | Type | Required | Description |
|---|---|---|---|
Authorization | string · header | Required | The account Access Token from the OpenAPI dashboard — passed as the raw token (no Bearer prefix) and included in the signature calculation. |
X-Api-Key | string · header | Required | Your App Key. |
X-Timestamp | string · header | Required | Request timestamp in seconds (Unix epoch). |
X-Api-Signature | string · header | Required | HMAC-SHA256 signature. Format: HMAC-SHA256 SignedHeaders=authorization;x-api-key;x-timestamp, Signature=. |
When Start Conversation returns status = interrupted, the Agent is waiting for more information from you. Send your answers via this endpoint and the paused run resumes from the interrupt point, until it succeeds, gets interrupted again, or fails.
A single round of conversation may be interrupted multiple times: if the run returns interrupted again after continuing, call this endpoint again with the new interrupt.
As with Start Conversation, choose blocking / SSE streaming response mode with the Accept header.
Request
Path parameters
| Name | Type | Required | Description |
|---|---|---|---|
agent_id | string | Required | Agent UID. |
chat_uid | string | Required | Conversation UID of the interrupted run. |
message_id | string | Required | ID of the interrupted message to continue. |
Request body
| Name | Type | Required | Description |
|---|---|---|---|
answers_by_tool_call | object | Required | Answers keyed by tool-call ID, providing the information the Agent asked for so the interrupted run can resume. |
Response
Response properties
| Name | Type | Required | Description |
|---|---|---|---|
chat_uid | string | Required | Conversation UID. |
message_id | string | Required | Message ID. |
status | string | Required | Run status, e.g. `succeeded`, `interrupted`. |
answer | string | Optional | The Agent's answer text. |
references | array | Optional | Reference sources cited in the answer. |
elapsed_time | number | Optional | Elapsed run time in seconds. |
Response JSON example
{
"code": 0,
"message": "success",
"data": {
"chat_uid": "ct_9f2c1a5b",
"message_id": "43",
"status": "succeeded",
"answer": "Over the past month, Tesla (TSLA.US)...",
"references": [],
"elapsed_time": 2.74
}
}Error code
See the Error Codes page for the full list of error codes.