/**
 * Cross-run comparison for dsh-eval: two persisted run reports become a row
 * list of metric values and deltas, rendered as a markdown table.
 *
 * @module dsh-eval/compare
 */
import type { EvalRun } from './types.ts';
import { type PairedDelta, type SignTestOutcome } from './stats.ts';
/** One compared metric row. */
export interface CompareRow {
    /** Metric label. */
    metric: string;
    /** Run A's rendered value. */
    a: string;
    /** Run B's rendered value. */
    b: string;
    /** Signed delta (`b - a`) for numeric rows, or a dash for text rows. */
    delta: string;
}
/** Paired same-case statistics over two runs. */
export interface PairedStats {
    /** Number of case x trial pairs completed in both runs. */
    pairs: number;
    /** Pairs where run B beat run A on the primary metric. */
    wins: number;
    /** Pairs where run A beat run B on the primary metric. */
    losses: number;
    /** Pairs with equal primary-metric outcomes. */
    ties: number;
    /** The metric used for win/lose/tie classification. */
    primaryMetric: 'task success' | 'tool selection accuracy' | 'final answer score';
    /** Exact two-sided sign test over the discordant pairs of the primary metric. */
    test: SignTestOutcome;
    /** Paired step delta (`b - a`) with its bootstrap interval, or null when no pair is numeric. */
    stepsDelta: PairedDelta | null;
    /** Paired token delta (`b - a`) with its bootstrap interval, or null when no pair is numeric. */
    tokensDelta: PairedDelta | null;
    /** Paired judge-score delta (`b - a`) with its bootstrap interval, or null without verdicts. */
    scoreDelta: PairedDelta | null;
}
/**
 * Pair both runs' trials by case id and trial index and compute win/lose/tie
 * plus mean deltas. Trials are paired as-is; the runs' `seed` is recorded
 * provenance for the pairing, not a guarantee of identical model output.
 * @param a - the baseline run.
 * @param b - the candidate run.
 * @returns paired statistics, or null when no trial is completed in both runs.
 */
export declare function pairedCompare(a: EvalRun, b: EvalRun): PairedStats | null;
/**
 * Build the comparison rows between two runs.
 * @param a - the baseline run.
 * @param b - the candidate run.
 * @returns the row list in display order.
 */
export declare function compareRuns(a: EvalRun, b: EvalRun): CompareRow[];
/**
 * Render comparison rows as a markdown table.
 * @param rows - the rows from {@link compareRuns}.
 * @returns the markdown text.
 */
export declare function renderCompareMarkdown(rows: readonly CompareRow[]): string;