Sign in
Assistants

Trigger a manual test run

Initiates immediate execution of a specific assistant test

post/ai/assistants/tests/{test_id}/runs

Path parameters

test_idstring required

Unique identifier of the test.

Headers

Idempotency-Keystring

Optional opaque, unquoted key for safely retrying the same logical request. Keys must contain 1 to 255 letters, numbers, hyphens, or underscores. Generate a unique UUID v4 for each operation and reuse it only when retrying that operation with the same request. Invalid headers—including duplicate, empty, malformed, or overlong values—return 400 with error code 10015. A request already in progress with the same key returns 409; reusing the key with a different request returns 422. Only successful responses are replayed, for up to 24 hours. Do not include sensitive data in the key.

Request body

destination_version_idstring

Optional assistant version ID to use for this test run. If provided, the version must exist or a 400 error will be returned. If not provided, test will run on main version

Example request

{
  "destination_version_id": "123e4567-e89b-12d3-a456-426614174000"
}

Response

Returns the created test run with execution details and status

run_idstring uuid required

Unique identifier for this specific test run execution.

test_idstring uuid required

Identifier of the assistant test that was executed.

status'pending' | 'starting' | 'running' | 'passed' | 'failed' | 'error' required

Represents the lifecycle of a test:

  • 'pending': Test is waiting to be executed.
  • 'starting': Test execution is initializing.
  • 'running': Test is currently executing.
  • 'passed': Test completed successfully.
  • 'failed': Test executed but did not pass.
  • 'error': An error occurred during test execution.
triggered_bystring required

How this test run was initiated (manual, scheduled, or API).

completed_atstring date-time

Timestamp when the test run finished execution.

logsstring

Detailed execution logs and debug information.

conversation_idstring

Identifier of the conversation created during test execution.

conversation_insights_idstring

Identifier for conversation analysis and insights data.

test_suite_run_idstring uuid

Identifier linking this run to a test suite execution batch.

created_atstring date-time required

Timestamp when the test run was created and queued.

updated_atstring date-time

Timestamp of the last update to this test run.

Example response

{
  "run_id": "987fcdeb-51a2-43d1-b456-426614174000",
  "test_id": "123e4567-e89b-12d3-a456-426614174000",
  "triggered_by": "cron",
  "created_at": "2024-01-24T10:30:00Z"
}

Changes

Changed in 2 of the 99 revisions of this API.136

  • 9621f6123ebc2See the full diff
    • ●

      added the new 10011 enum value to the // response property for the response status

      response-property-enum-value-added

    • ●

      added the new domain_graduation_limit_exceeded enum value to the // response property for the response status

      response-property-enum-value-added

  • a6a61a29ecdd116See the full diff
    • ▲

      the response's body type changed from object to no type for status

      response-body-type-changed

    • ●

      removed the optional property from the response with the status

      response-optional-property-removed

    • ○

      added the new optional header request parameter Idempotency-Key

      new-optional-request-parameter

    • ○

      added to the response body anyOf list for the response status

      response-body-any-of-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    This revision also has 34 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

Of the 99 revisions, 1 has no diff computed.