Get a thread
One external agent thread turn by turn: every model call as an llm step and the tool calls between calls as tool steps. Message bodies come from the newest stored request trace (bodies says how much was found).
curl --request GET \
--url https://api.veri.studio/v1/deployments/{deployment_id}/threads/{thread_id} \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.veri.studio/v1/deployments/{deployment_id}/threads/{thread_id}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.veri.studio/v1/deployments/{deployment_id}/threads/{thread_id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"object": "<string>",
"id": "<string>",
"deployment_id": "<string>",
"deployment_name": "<string>",
"thread_id": "<string>",
"agent": {
"key": "<string>",
"name": "<string>",
"kind": "<string>"
},
"status": "<string>",
"started_at": "2023-11-07T05:31:56Z",
"last_activity_at": "2023-11-07T05:31:56Z",
"bodies": "<string>",
"models": [
"<string>"
],
"totals": {
"turns": 123,
"llm_calls": 123,
"tool_calls": 123,
"tool_errors": 123,
"messages": 123,
"prompt_tokens": 123,
"cached_prompt_tokens": 123,
"completion_tokens": 123,
"errors": 123,
"duration_ms": 123
},
"turns": [
{
"index": 123,
"started_at": "2023-11-07T05:31:56Z",
"latency_ms": 123,
"prompt_tokens": 123,
"completion_tokens": 123,
"llm_calls": 123,
"tool_calls": 123,
"steps": [
{
"request_id": "<string>",
"model": "<string>",
"started_at": "2023-11-07T05:31:56Z",
"latency_ms": 123,
"prompt_tokens": 123,
"cached_prompt_tokens": 123,
"completion_tokens": 123,
"status_code": 123,
"tool_calls": [
{
"name": "<string>",
"id": "<string>",
"arguments": "<string>"
}
],
"kind": "llm",
"ttft_ms": 123,
"error": "<string>",
"finish_reason": "<string>",
"content": "<string>",
"reasoning": "<string>"
}
],
"user": "<string>",
"reply": "<string>"
}
],
"scores": [
{
"object": "<string>",
"id": "<string>",
"evaluator_id": "<string>",
"evaluator_version": 123,
"name": "<string>",
"target_type": "<string>",
"value": "<unknown>",
"source": "<string>",
"status": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"request_id": "<string>",
"deployment_id": "<string>",
"thread_id": "<string>",
"target_revision": "<string>",
"experiment_id": "<string>",
"item_id": "<string>",
"passed": true,
"reasoning": "<string>",
"error": "<string>",
"author": "<string>",
"model_version_id": "<string>",
"monitor_id": "<string>",
"confidence": 123,
"probabilities": {}
}
],
"tools": [
{}
]
}Authorizations
API key with the vk_ prefix. Create one from the dashboard.
Path Parameters
Deployment ID
The X-Veri-Thread-Id the requests carried
Response
Always "thread".
{deployment_id}:{thread_id}.
Who a conversation belongs to.
Show child attributes
Show child attributes
active | idle
captured (the newest call's body is stored) | partial (an older call's is) | none (no stored bodies: trace bodies off or purged).
Show child attributes
Show child attributes
The latest 1000 model calls, oldest first, grouped into turns.
Show child attributes
Show child attributes
Thread and trace scores on this thread, newest first.
Show child attributes
Show child attributes
The tools the agent declared, from the stored body.
curl --request GET \
--url https://api.veri.studio/v1/deployments/{deployment_id}/threads/{thread_id} \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.veri.studio/v1/deployments/{deployment_id}/threads/{thread_id}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.veri.studio/v1/deployments/{deployment_id}/threads/{thread_id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"object": "<string>",
"id": "<string>",
"deployment_id": "<string>",
"deployment_name": "<string>",
"thread_id": "<string>",
"agent": {
"key": "<string>",
"name": "<string>",
"kind": "<string>"
},
"status": "<string>",
"started_at": "2023-11-07T05:31:56Z",
"last_activity_at": "2023-11-07T05:31:56Z",
"bodies": "<string>",
"models": [
"<string>"
],
"totals": {
"turns": 123,
"llm_calls": 123,
"tool_calls": 123,
"tool_errors": 123,
"messages": 123,
"prompt_tokens": 123,
"cached_prompt_tokens": 123,
"completion_tokens": 123,
"errors": 123,
"duration_ms": 123
},
"turns": [
{
"index": 123,
"started_at": "2023-11-07T05:31:56Z",
"latency_ms": 123,
"prompt_tokens": 123,
"completion_tokens": 123,
"llm_calls": 123,
"tool_calls": 123,
"steps": [
{
"request_id": "<string>",
"model": "<string>",
"started_at": "2023-11-07T05:31:56Z",
"latency_ms": 123,
"prompt_tokens": 123,
"cached_prompt_tokens": 123,
"completion_tokens": 123,
"status_code": 123,
"tool_calls": [
{
"name": "<string>",
"id": "<string>",
"arguments": "<string>"
}
],
"kind": "llm",
"ttft_ms": 123,
"error": "<string>",
"finish_reason": "<string>",
"content": "<string>",
"reasoning": "<string>"
}
],
"user": "<string>",
"reply": "<string>"
}
],
"scores": [
{
"object": "<string>",
"id": "<string>",
"evaluator_id": "<string>",
"evaluator_version": 123,
"name": "<string>",
"target_type": "<string>",
"value": "<unknown>",
"source": "<string>",
"status": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"request_id": "<string>",
"deployment_id": "<string>",
"thread_id": "<string>",
"target_revision": "<string>",
"experiment_id": "<string>",
"item_id": "<string>",
"passed": true,
"reasoning": "<string>",
"error": "<string>",
"author": "<string>",
"model_version_id": "<string>",
"monitor_id": "<string>",
"confidence": 123,
"probabilities": {}
}
],
"tools": [
{}
]
}
