Skip to main content
GET
Retrieve a task run

Authorizations

Authorization
string
header
required

Secret key (sk_live_...)

Path Parameters

run_id
string
required

Unique identifier for the task run (prefixed with trun_).

Query Parameters

include
string

Comma-separated list of additional fields to include in the response. Supported values: input, storage, artifacts. Sections are omitted from the response (not returned as null) when their flag is not present.

Response

OK

A task run object representing a single execution of a task.

id
string
required

Unique identifier for the task run, prefixed with trun_.

object
string
required

Always task_run.

status
string
required

Run status: queued, running, canceling, interaction_required, review_required, completed, canceled, or failed.

result
null | string
required

Run result after completion: success, failure, or unknown. Null while running.

task_id
string
required

The task that was executed. Prefixed with task_.

credential_id
null | string
required

The credential used for authentication, if any. Prefixed with cred_.

session_id
null | string
required

The session this run executed within, if any. Prefixed with sess_.

agent_id
string
required

The agent that executed this run. Prefixed with agt_.

source_id
null | string
required

The source this run connected to, if any. Prefixed with src_.

runtime_ms
required

Execution time in milliseconds.

output
null | any
required

Output data produced by the task execution.

errors
null | object[]
required

Error details if the run failed. Same structure as API-level errors.

interaction
null | any
required

Interaction details when the run is paused waiting for user input (e.g. MFA code, security question).

created_at
string<date-time>
required

ISO 8601 timestamp of when the resource was created.

updated_at
string<date-time>
required

ISO 8601 timestamp of when the resource was last updated.

request_id
string
required

Unique identifier for the API request. Include this when contacting support.

input
null | any

Input data provided when the run was created.

tokenized
null | string[]

Names of input fields whose values were tokenized when the run was created. The listed fields are removed from input. Returned alongside input (only when include=input is requested and one or more fields were vaulted); omitted otherwise.

storage
null | object[]

Files captured during the run, each with inline extraction (if any). Returned only when include=storage is requested.

artifacts
null | object

Run-level visibility artifacts (screenshots). Returned only when include=artifacts is requested.