import type { EvalReport } from "./eval.js";
import { type Comparison } from "./stats.js";
/** Bumped only on a breaking change to the on-disk shape. */
export declare const BASELINE_VERSION = 1;
/** The committed baseline: the recorded `EvalReport`s, keyed by report name. */
export interface BaselineFile {
    readonly version: number;
    /** ISO-8601 timestamp the baseline was recorded (provenance / future trend). */
    readonly recordedAt: string;
    /** Recorded reports, keyed by `report.name` (so multiple eval files coexist). */
    readonly reports: Record<string, EvalReport>;
}
/** How a metric moved between baseline and current run. */
export type DiffStatus = "regressed" | "improved" | "unchanged";
/** One arm×metric comparison of a current run against the baseline. */
export interface MetricDiff {
    /** The `report.name` this entry belongs to. */
    readonly report: string;
    readonly arm: string;
    readonly metric: string;
    readonly status: DiffStatus;
    /** Welch comparison, current vs. baseline (`delta = current − baseline`). */
    readonly comparison: Comparison;
}
export interface BaselineDiff {
    /** Every arm×metric present in BOTH the baseline and the current run. */
    readonly entries: readonly MetricDiff[];
    /** The subset that regressed (significant move in the bad direction). */
    readonly regressions: readonly MetricDiff[];
    /** The subset that improved (significant move in the good direction). */
    readonly improvements: readonly MetricDiff[];
    /** True when there are no regressions — the gate. */
    readonly passed: boolean;
}
export interface DiffOptions {
    /** Significance level for the Welch test. Default 0.05. */
    readonly alpha?: number;
    /**
     * Metrics where a DECREASE is the improvement (e.g. `cost`, `latency`,
     * `turns`). For these, a significant increase is the regression. Everything
     * else is treated as higher-is-better.
     */
    readonly lowerIsBetter?: readonly string[];
}
/** Build a `BaselineFile` envelope from a run's reports (keyed by name). */
export declare function toBaselineFile(reports: readonly EvalReport[], recordedAt?: string): BaselineFile;
/** Parse + validate a baseline JSON string (throws on a bad version/shape). */
export declare function parseBaselineFile(json: string): BaselineFile;
/**
 * Diff a current run against a committed baseline. Compares every arm×metric
 * present in both (by report name), flagging a *significant* move in the
 * undesired direction as a regression. Metrics absent from one side are skipped
 * (a new arm/metric is not a regression).
 */
export declare function diffReports(baseline: BaselineFile, current: readonly EvalReport[], opts?: DiffOptions): BaselineDiff;
/** Format a baseline diff as a compact console report. */
export declare function formatBaselineDiff(diff: BaselineDiff): string;
/**
 * Render a baseline diff as JUnit XML — one `<testcase>` per arm×metric, a
 * `<failure>` for each regression. Lets a CI provider show eval regressions in
 * the same place as unit-test failures.
 */
export declare function diffToJUnit(diff: BaselineDiff): string;
/** Read + parse a baseline file, or null if it doesn't exist yet. */
export declare function readBaseline(path: string): BaselineFile | null;
/** Write reports as the committed baseline (pretty JSON, parent dirs created). */
export declare function writeBaseline(path: string, reports: readonly EvalReport[]): void;
//# sourceMappingURL=eval-baseline.d.ts.map