Skip to main content
GET
/
agents
/
{id}
/
events
Error
A valid request URL is required to generate request examples
[
  {
    "id": "<string>",
    "timestamp": "2023-11-07T05:31:56Z",
    "type": "command_start",
    "tool": "shell",
    "input_summary": "<string>",
    "output_summary": "<string>",
    "duration_ms": 123,
    "success": true,
    "metadata": {}
  }
]

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
id
string<uuid>
required

Query Parameters

​
tail
integer
default:100

Number of tail events

​
follow
enum<string>

If "true", stream events via SSE

Available options:
true,
false

Response

Event output (JSON array or SSE stream)

​
id
string

Event ID. Container events use UUID format. Inference events use "inference-" prefix to avoid collision with container event IDs.

​
timestamp
string<date-time>
​
type
enum<string>

Event type. Container events use command_start/complete, file_*, etc. Inference events use inference_complete for success, or inference_ for non-success statuses (error, rate_limited, budget_exceeded, client_disconnect).

Available options:
command_start,
command_complete,
file_read,
file_write,
directory_list,
identity_read,
health_check,
inference_complete,
inference_error,
inference_rate_limited,
inference_budget_exceeded,
inference_client_disconnect
​
tool
enum<string>

Tool category. Inference events always have tool=inference.

Available options:
shell,
filesystem,
runtime,
identity,
health,
inference
​
input_summary
string

Truncated human-readable input (max 200 chars). For inference events, formatted as "model_name (request_type)".

​
output_summary
string | null

Metadata-only result summary. For container events: exit codes, byte counts. For inference events: "input_tokens+output_tokens tokens, $cost, latency_ms". Never contains raw output or prompt/completion content.

​
duration_ms
integer | null
​
success
boolean | null
​
metadata
object

Additional structured data. For inference events, contains: model_name (string), request_type (string), status (string), input_tokens (integer), output_tokens (integer), cost_usd (number). No prompt or completion content is included.