Prompts

Submit a prompt for execution

Queues a prompt on a project's agent. The prompt is created with status pending; the agent picks it up on its next heartbeat (every 15 seconds) and transitions it to running — there is no separate execute call. Poll GET /api/v1/prompts/{id} or GET /api/v1/logs?promptId=... for progress.

Requires a token that can be attributed to a user: a CLI token (oclt_), or an org API key (oak_) with the prompts:write scope. Agent tokens (oat_) are rejected — a token that lives on the machine which would run the prompt cannot enqueue its own work.

A project you cannot reach returns 404, not 403, so ids cannot be probed.

post/api/v1/prompts

Request

  • Base URL: https://getorquesta.com
  • URL: https://getorquesta.com/api/v1/prompts
  • Auth: one of:
    • HTTP bearer
    • API key in header X-API-Key

Request body

projectIdstring uuid required
contentstring required

The prompt text.

contextobject

Arbitrary JSON passed through to the agent.

tagsstring[]
source'api' | 'dashboard'
workstreamIdstring uuid

Run the prompt in this workstream: its agent (the microVM when the workstream runs there, which is woken), working directory and branch. 404 when the workstream is not in the project.

Response

Prompt created and queued.

Example response

{
  "prompt": {
    "status": "pending"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.