CEcekura
Evaluators

Run evaluators against a Pipecat Cloud deployment (project credentials, v2)

Changed on

PIPECAT CLOUD VOICE RUN (project credentials, v2): Execute evaluators against an agent deployed on Pipecat Cloud using credentials configured at the project level. Cekura creates the sessions; you don't pass per-scenario room URLs (that's the v1 endpoint). Requires Pipecat Cloud credentials with pipecat_agent_name set on the agent or project.

Cost: voice-simulation rate per run. Run-count math: total runs = len(scenarios) × frequency.

Per-request session_config override is allowed; merges over agent defaults.

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

  • scenarios_run_pipecat_v1 — manual room URLs per scenario
  • scenarios_run_voice — phone / SIP voice run
  • scenarios_run_livekit_v2 — LiveKit (project credentials, v2)
post/test_framework/v2/scenarios/run_scenarios_pipecat_v2/

Request

  • Base URL
    https://api.cekura.ai
  • URL
    https://api.cekura.ai/test_framework/v2/scenarios/run_scenarios_pipecat_v2/
  • Auth
    • API key in header X-CEKURA-API-KEY
    • or HTTP bearer
    • or HTTP bearer

Request body

namestring nullable

Optional name for the scenario result

frequencyinteger

Number of times to run each scenario (default: 1)

agentinteger nullable

Cekura agent ID to run against. Overrides the scenarios' agent.

personality_idsinteger[] nullable

List of personality IDs to override for this run. If not provided, uses the scenario's default personality.

test_profile_idsinteger[] nullable

List of test profile IDs to override for this run. If not provided, uses the scenario's default test profile.

mock_tool_namesstring[] nullable

Names of mock tools to activate for this run. Omit (or send null) to mock every tool configured on the agent; send an empty list to mock none so every tool keeps its original endpoint; send specific names to mock only those.

personality_idinteger nullable

Single personality ID override. Merged into personality_ids; prefer personality_ids for multiple.

test_profile_idinteger nullable

Single test profile ID override. Merged into test_profile_ids; prefer test_profile_ids for multiple.

concurrency_limitinteger nullable

Optional cap on how many of this run's calls execute concurrently.

calls_per_secondnumber double nullable

Most calls started per second for this run, a number from 0.1 to 4 (e.g. 0.5 starts one call every 2 seconds). Leave unset for no limit.

Response

idinteger

ID of the result

agentinteger

ID of the agent

status'running' | 'completed' | 'failed' | 'pending' | 'in_progress' | 'evaluating' | 'in_queue' | 'timeout' | 'cancelled' | 'scaling_up'

Status of the result. Poll until it is completed, failed, timeout or cancelled. It stays non-terminal until every run has ended, then becomes completed if any run completed — even if runs failed their checks or others errored.

run_as_textboolean

Whether the scenario ran as text or not

created_atstring date-time

Example response

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

Changes