ImportAgentRunRequest

Example Usage

import { ImportAgentRunRequest } from "@meetkai/mka1/models/components";

let value: ImportAgentRunRequest = {
  suiteId: "<id>",
  agentName: "<value>",
  model: "Model S",
};

Fields

Field	Type	Required	Description
suiteId	string	✔️	Existing suite to import into. Its manifest defines the task set, so create the suite first.
suiteVersion	number	➖	Defaults to the suite's active version.
agentName	string	✔️	The harness agent, e.g. omp.
agentVersion	string	➖	N/A
agentEffort	string	➖	Reasoning-effort setting, e.g. medium. Part of the leaderboard's row identity, so the same agent and model at two efforts stay two rows.
model	string	✔️	N/A
costUsd	number	➖	Total spend for the job. Falls back to the sum of the trials' own costs when omitted.
createdAt	number	➖	When the job ran, unix seconds. Defaults to now — set it when backfilling, since the board orders by this.
metadata	Record<string, string>	➖	N/A
idempotencyKey	string	➖	Reusing a key returns the run created the first time instead of importing a second copy. Without one, a retried upload silently doubles the trials behind a board row.
trials	components.ImportAgentRunRequestTrials[]	➖	May be empty when opening a run to stream trials into. A one-shot import sends them all here.
expectedTrials	number	➖	How many trials the job will produce. Sets the run's total up front so the console shows real progress (12/89) while it streams, instead of 12/12 that grows.
finalize	boolean	➖	False opens the run in_progress for POST /evals/runs/{run_id}/trials to fill. Leaderboards only count completed runs, so a streaming run stays off the board until it is finalized.