@adonis-agora/agent
Version:
Governed, durable-backed AI agent (chat + tool-calling + governance) for AdonisJS — part of the Agora ecosystem.
15 lines • 754 B
JavaScript
/**
* The evaluation SPI: a {@link Scorer} turns ONE stored run into a number plus the sentence that
* justifies it. Everything else here (the batch runner, the score store, the summaries) is plumbing
* around that one call.
*
* Scoring is offline-first. A {@link ScorableRun} is assembled from what the agent already persisted
* — the run row, its transcript, its tool calls and their HITL outcomes — so a scorer never sits
* inside a turn, never adds latency to one, and can be re-run over history the day a new scorer is
* written.
*/
/** Clamp a computed score into the `0..1` range {@link ScoreResult.score} promises. */
export function clampScore(value) {
return Math.min(1, Math.max(0, value));
}
//# sourceMappingURL=types.js.map