PIPECAT WEBRTC RUN (manual room URLs, v1): Execute evaluators against an agent running on Pipecat / Daily.co WebRTC. Each scenario entry carries its own pipecat_room_url and optional token. For project-credential-based runs (no per-scenario URL), use scenarios_run_pipecat_v2 instead.

Run-count: one run per entry in scenarios — this endpoint does not support frequency or personality/test-profile multipliers. To run the same scenario multiple times, include it multiple times in the scenarios list.

When to use this vs others (pick the endpoint matching the agent's configured connection — check aiagents_retrieve):

• run_scenarios — real voice / phone / SIP call
• run_scenarios_text — text / SMS / chat mode
• run_scenarios_with_websockets — agent exposes a plain websocket URL (non-Pipecat)

Scheduled runs: WebRTC sessions are not generally scheduled. Use run_scenarios or run_scenarios_text via CronJob for recurring evaluator runs.

{
  "runs": [
    {
      "number": "+11234567890",
      "inbound_number": "+11234567890"
    }
  ],
  "created_at": "2025-02-25T21:00:01.990052Z"
}