List versions of an eval suite
const url = 'https://example.com/v1/eval-suites/example/versions?limit=25&includeTombstoned=false';const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url 'https://example.com/v1/eval-suites/example/versions?limit=25&includeTombstoned=false' \ --header 'Authorization: Bearer <token>'Cursor-paginated. Sort order is binding-defined (for example ascending semver). Defaults to active versions only. Pass ?includeTombstoned=true to include unregistered versions too, each with unregisteredAt: a retired suite (every version unregistered) answers too, with its versions to reinstate.
Authorizations
Section titled “Authorizations”Parameters
Section titled “Parameters”Path Parameters
Section titled “Path Parameters”EvalSuiteId — stable string chosen by the caller (e.g. acme.drafting-accuracy).
Query Parameters
Section titled “Query Parameters”1..100. Default 25.
Where the previous page ended: its nextCursor, as it came. A runtime that seals cursors takes one only for the same list, filters and caller, within a day; otherwise 400 bad-input, and the list starts again without it. Absent → first page.
When true, the response includes soft-tombstoned versions in addition to active ones. Tombstoned rows carry an unregisteredAt ISO timestamp; active rows omit the field. Default: false (active-only).
Responses
Section titled “Responses”Page of eval suite versions.
object
object
The test set’s project: every version of a test set is in the one project. Absent when the runtime doesn’t record it: a pack kindgi dev serves from disk, or a runtime before Kindgi 0.1.6.
Semver — publishing a modified suite produces a new version.
Kind-specific suite body. For accuracy, typically { cases: [{ input, expectedOutput }], grader?: { adapterId, config? } }. For pairwise, typically { prompts, variantA, variantB }. For regression, typically { baseline, cases }. For human-review, typically { rubric, reviewerRole }. For benchmark, typically { benchmark: { name, version } }. For custom, typically { handler: { modulePath, entrypointPath }, cases }.
object
Present only on an unregistered version: one GET …/versions?includeTombstoned=true lists, or a retired test set (every version unregistered) as GET /v1/eval-suites?includeRetired=true lists it.
Example
{ "data": [ { "kind": "accuracy" } ]}bad-input: a cursor this list didn’t issue.
object
object
Stable machine-readable discriminant. Values match domain error codes (see docs/API-ROUTE-CONVENTIONS.md §4.3).
Optional, kind-specific.
object
Server-assigned request id; also echoed via X-Request-Id header.
Examplegenerated
{ "error": { "code": "example", "message": "example", "details": {}, "requestId": "example" }}Missing / malformed / expired / revoked bearer token.
object
object
Stable machine-readable discriminant. Values match domain error codes (see docs/API-ROUTE-CONVENTIONS.md §4.3).
Optional, kind-specific.
object
Server-assigned request id; also echoed via X-Request-Id header.
Examplegenerated
{ "error": { "code": "example", "message": "example", "details": {}, "requestId": "example" }}No eval suite was ever registered with that id under this tenant.
object
object
Stable machine-readable discriminant. Values match domain error codes (see docs/API-ROUTE-CONVENTIONS.md §4.3).
Optional, kind-specific.
object
Server-assigned request id; also echoed via X-Request-Id header.
Examplegenerated
{ "error": { "code": "example", "message": "example", "details": {}, "requestId": "example" }}See also
GET /v1/eval-suites/{suiteId}: Fetch an eval suite (latest version)GET /v1/eval-suites/{suiteId}/versions/{version}: Fetch a specific eval suite versionPOST /v1/eval-suites/{suiteId}/versions/from-judgments: Build a test set from judgmentsGET /v1/eval-suites/{suiteId}/versions/{version}/cases: List the cases of a judged eval suite version- Error code
bad-input - Every error code