Start a run

Starts the agent bound to your api key. The key implies the agent — a 1:1 binding — so there is no agent id to pass and any supplied in the body is ignored. **Asynchronous by default.** The response is `202` carrying a `runUid` *before* any work begins, so the handle can never be lost to a client timeout. Poll `GET /agent/runs/{runUid}` for progress and the result. Pass `?wait=true` to hold the connection for short calls instead. That wait has a server-side ceiling; when it is reached you receive the same async envelope and the run continues — waiting can degrade into polling, never into an orphaned run. If the agent reaches a step its policy marks high-risk, the run **pauses** rather than proceeding, and `status` becomes `pending_approval`. A human approves it in the console. An `autoApprove` sent by a client is never honoured: an external caller is the least-trusted principal and may only tighten.

curl -X POST "https://example.com/497f6eca-6276-4993-bfeb-53cbbbba6f08/agent/invoke" \  -H "Content-Type: application/json" \  -d '{    "message": "Refund the last order for customer 4821 and explain why."  }'

{  "runUid": "string",  "status": "string",  "resumable": true,  "message": "string",  "pendingSteps": [    {      "stepIndex": 0,      "tool": "string",      "riskLevel": "string",      "input": {}    }  ],  "steps": [    {      "stepIndex": 0,      "tool": "string",      "status": "string",      "output": {},      "detail": "string"    }  ],  "actions": {    "poll": "string",    "dashboard": "string"  }}