Get an agent's A2A card
AuthorizationBearer <token>An application key of the Tenant (PUT /v1/tenant/keys/{keyId}), or Studio's key, derived from the admin key. With Nylorun-Subject and Nylorun-Scopes, it acts for that person, narrowed to those scopes. Never accepted from a browser (Origin).
agentId*stringNylorun-Protocol*stringThe protocol version, 18
Nylorun-Subject?stringThe person an application key acts for
Nylorun-Scopes?stringThe subject's space-separated scopes; required with a subject
The card
application/json- response
The agent's A2A card: this Runtime's JSON-RPC interface (A2A 1.0), streaming: false, pushNotifications when the Runtime has a push secret, and the Nylorun profile v2 extensions, all required: false
name*stringdescription?stringskills?array<unknown>[key: string]?unknowncurl -X GET "https://example.com/v1/a2a/agents/string/card" \ -H "Nylorun-Protocol: string"{ "name": "string", "description": "string", "skills": [ null ], "property1": null, "property2": null}Cancel a thread's running turn POST
Previous Page
Call an agent over A2A POST
A2A 1.0 JSON-RPC, for a subject, under the Nylorun profile v2 (Host feature `a2a-profile-v2`). `SendMessage` blocks up to the Runtime limit `a2aWaitMs` (5 minutes by default; then the task is answered still `WORKING`) unless `returnImmediately`; `GetTask` (with `historyLength`), `CancelTask` and `ListTasks`; and the four push notification config methods, plus `configuration.taskPushNotificationConfig` in `SendMessage`: each update is POSTed as one `StreamResponse`, signed with Standard Webhooks (`webhook-id`, `webhook-timestamp`, `webhook-signature` with the Runtime's `a2a.push.secret`) and `X-A2A-Notification-Token`, at least once, retried for up to 24 hours, to hosts the Runtime allows (`a2a.push.allowHosts` for private ones). A message to a busy context is queued and answered with the task that will take it (`TASK_STATE_SUBMITTED`); `message.metadata.delivery: "reject"` asks for `UnsupportedOperationError` (reason `CONTEXT_BUSY`) instead, and `"steer"` (Host feature `a2a-steer`) steers it into the running turn, as a session message's `delivery: "steer"`: the turn takes it before its next step and the task is that turn's; to an idle context, a workflow's, or a turn past its last step it is an ordinary message. The task answered to a steer carries `metadata.delivery`: `steered`, or `queued` when it started a turn or waits as a queued message. A queued task never waits for good (Host feature `queue-recovery`): when its Agent refuses its turn's start (a disk copy, a lost pod), the start is tried again until the Runtime limit `queuedStartMs` (15 minutes by default), and then, or at once for a refusal no retry changes, the task is `TASK_STATE_FAILED` with a status message saying why; `CancelTask` on a queued task takes it out of the queue, a task running in the context or not, and answers `TASK_STATE_CANCELED`. Both are pushed. `message.metadata.removeTools` (Host feature `remove-tools`) names the tools a new message's turn may not use, as a session message's `removeTools`. `message.metadata.role` (Host feature `model-roles`) opens a new context's session on that model role, as `PUT /v1/sessions/{id}`'s `role`; a role the Agent's version does not declare is `InvalidParams`. A message is text, one data part, or text with `raw` files (stored as artifacts of the context's session) and `url` files (fetched by the Runtime), each at most the Runtime limit `inlineFileBytes` (20 MiB by default). An approval, question or connection the task waits for (`AUTH_REQUIRED` or `INPUT_REQUIRED`) is shown under `interactions/v1` and answered on the same task with `{ interactionId, approved }` or `{ interactionId, value }` under that URI in the message's `metadata`; text never approves. Artifacts carry the turn's output and the files it wrote, as `url` parts at `/v1/a2a/files/…` with `files/v1`; the task's metadata carries `progress/v1`, `telemetry/v1` and `effects/v1`. Extension data is answered only for the extensions activated with `A2A-Extensions`. A context is one session per subject, agent and `contextId`; a task is one turn. JSON-RPC errors are answered with 200; limits, scopes and unavailable streams stay HTTP errors. Not served: streaming, `GetExtendedAgentCard`.