AppendAgentTrialsRequestTrials
Example Usage
typescript
import { AppendAgentTrialsRequestTrials } from "@meetkai/mka1/models/components";
let value: AppendAgentTrialsRequestTrials = {
taskId: "<id>",
sampleIndex: 563684,
};Fields
| Field | Type | Required | Description |
|---|---|---|---|
taskId | string | ✔️ | Must already exist in the target suite version's manifest; unknown ids are rejected rather than invented. |
sampleIndex | number | ✔️ | N/A |
status | components.AppendAgentTrialsRequestStatus | ➖ | failed means no score was produced at all. An agent timeout is NOT that — the harness still runs the verifier and scores the trial, so it stays completed and carries its exception in error. |
prompt | string | ➖ | The task instruction. |
target | string | ➖ | N/A |
outputText | string | ➖ | What decided the score — the verifier's output. The agent's session goes to the trajectory route. |
scores | Record<string, number> | ➖ | Metric values for this trial, e.g. { "reward": 1, "resolved": 1 }. The board averages reward by default. |
error | Record<string, any> | ➖ | The exception this trial recorded, if any. Does not by itself make the trial a failure. |
costUsd | number | ➖ | N/A |
inputTokens | number | ➖ | N/A |
outputTokens | number | ➖ | N/A |
cachedTokens | number | ➖ | The share of input_tokens served from the provider's prompt cache. |
phaseTimings | Record<string, any> | ➖ | N/A |