curl --request POST \
--url https://api.calibrate.artpark.ai/traces \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"agent_id": "<string>",
"input": "<string>",
"output": {
"response": "<string>",
"tool_calls": [
{
"tool": "<string>",
"arguments": {},
"output": "<unknown>"
}
]
}
}
'import requests
url = "https://api.calibrate.artpark.ai/traces"
payload = {
"agent_id": "<string>",
"input": "<string>",
"output": {
"response": "<string>",
"tool_calls": [
{
"tool": "<string>",
"arguments": {},
"output": "<unknown>"
}
]
}
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"uuid": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
"created_at": "<string>",
"message_id": "<string>",
"conversation_id": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Create trace
Store a production agent turn and its conversation history for later review
curl --request POST \
--url https://api.calibrate.artpark.ai/traces \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"agent_id": "<string>",
"input": "<string>",
"output": {
"response": "<string>",
"tool_calls": [
{
"tool": "<string>",
"arguments": {},
"output": "<unknown>"
}
]
}
}
'import requests
url = "https://api.calibrate.artpark.ai/traces"
payload = {
"agent_id": "<string>",
"input": "<string>",
"output": {
"response": "<string>",
"tool_calls": [
{
"tool": "<string>",
"arguments": {},
"output": "<unknown>"
}
]
}
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"uuid": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
"created_at": "<string>",
"message_id": "<string>",
"conversation_id": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Authorizations
API key for authentication
Body
ID of the agent that produced the turn. Must be an agent in your workspace
1 - 36What the agent was given for this turn. For a general agent, the standalone prompt as a string. For a conversation agent, the history up to the reported output, oldest turn first, in OpenAI chat format
1 - 50000What the agent produced for this turn
Show child attributes
Show child attributes
Your own ID for the last user message in input, stored for reference only. Omit if you have none
1 - 255Your own ID for the conversation this turn belongs to, stored for reference only. Omit if you have none
1 - 255Key-value pairs stored with the trace. Prefer OTel gen_ai.* key names where they fit. Omit if you have none
100Show child attributes
Show child attributes
Your own tags for this turn, such as an environment or a release. Matched exactly when filtering, so keep the spelling stable. Omit if you have none
501 - 128Response
Successful Response
Unique ID for the trace
36"f47ac10b-58cc-4372-a567-0e02b2c3d479"
When the trace was created (ISO 8601 UTC)
The message ID you sent, if any
The conversation ID you sent, if any