Create a test scenario
A simulated caller the eval engine plays against the agent and grades. Define passing here: assertions for anything with a right answer, rubrics for what only a reader can judge, workflowChecks for its functions. It never changes the agent.
Authorization
bearerAuth A personal access token from Settings > API tokens.
In: header
Path Parameters
Workspace slug (GET /me lists yours).
Agent slug within the workspace.
Header Parameters
A key you choose, such as a UUID, that makes this POST safe to retry. Within 24 hours the same key and request answers with the first successful answer and runs nothing, the same key with a different request answers 422 idempotency_key_reused, and a key whose request is still running answers 409 idempotency_key_in_use. A failed request keeps nothing, so the same key runs it again.
1 <= length <= 255Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
application/problem+json
curl -X POST "https://example.com/workspaces/string/agents/string/tests" \ -H "Content-Type: application/json" \ -d '{ "name": "string", "instructions": "string" }'{
"scenarioId": "string",
"property1": null,
"property2": null
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}{
"type": "http://example.com",
"title": "string",
"status": 0,
"detail": "string",
"code": "string",
"errors": [
{
"path": "string",
"message": "string"
}
],
"estimate": {},
"retryAfterSeconds": 0
}Fetch a source again POST
Re-read one knowledge-base source now, keeping its id and its sync schedule. Use after the page or site behind a URL source changed, or to retry a source that failed. The page is fetched fresh, never from a cache. Unchanged pages keep their passages; changed pages are re-embedded (a metered charge). A failed refresh keeps the previous passages and reports the error. Returns the source's status, chunk count and what the quality gate dropped (`rejectedChunkCount`, `rejectedReasons`). A workspace-shared source cannot be refreshed from an agent.
Delete a test scenario DELETE
Permanently delete one scenario (scenarioId) or many (scenarioIds) from the agent's test library. The scenarios' run history is deleted with them (FK cascade), this cannot be undone, so confirm with the operator before bulk deletes. Resolve ids with list_scenarios first. Returns the deleted count; an id that isn't on this agent reports not-found rather than silently succeeding.