import { type JudgeSuiteArgs } from "../eval/judge/suite.js";
import type { PairwiseVerdict, SuiteVerdict } from "../eval/judge/types.js";
import type { EvalRecord } from "../eval/types.js";
/**
 * Stdlib binding: reads a JSONL statelog at `statelogPath` and returns its
 * structured EvalRecord (the eval record is a view of the statelog, never a
 * file). Composes the existing extractor pipeline; no separate logic here.
 */
export declare function _evalExtract(statelogPath: string): Promise<EvalRecord>;
/**
 * Stdlib binding for `eval judge`. Pairwise-judges two eval records against
 * a goal and returns the structured PairwiseVerdict. Delegates to the
 * existing `judgePairwise` so CLI and stdlib paths share judge behavior
 * (including the subprocess judge invocation through `runAgencyJudge`).
 */
export declare function _evalJudge(goal: string, recordPathA: string, recordPathB: string): Promise<PairwiseVerdict>;
/**
 * Stdlib binding for suite-aware eval judging. Compares two eval run
 * directories by input id and returns the suite verdict produced by the core
 * judgeSuite helper.
 */
export declare function _evalJudgeSuite(runA: string, runB: string, samples: number, confidenceThreshold: number, marginThreshold: number, positionBias: string, judge?: (args: JudgeSuiteArgs) => Promise<SuiteVerdict>): Promise<SuiteVerdict>;