/**
 * @copyright Sister Software
 * @license AGPL-3.0
 * @author Teffen Ellis, et al.
 *
 *   `mailwoman corpus audit` — per-source parquet-file count vs source_weight diagnostic.
 *
 *   Reads a corpus dir's manifest.json (or scans the parquet files directly), counts files per
 *   source, optionally loads a training config to pair the counts with the configured
 *   source_weights. It reports the estimated sampled-row distribution at training time.
 *
 *   Would have caught v0.3.0's "NAD = 411/674 train files × 2.0 weight = ~75% of sampled mix"
 *   finding before the v0.3.0 retrospective surfaced it.
 *
 *   Emits warnings to stderr and the audit table to stdout. never throws on an empty corpus.
 */
import { type PathBuilderLike } from "path-ts";
/**
 * Options for {@linkcode audit}.
 */
export interface AuditOpts {
    corpusDir: PathBuilderLike;
    configPath?: PathBuilderLike;
    /**
     * Sample at most N parquet files per split when counting sources.
     *
     * Default 100 for speed.
     * Bump to read the full set on a slow run.
     *
     * The first row of each file determines its source — corpus-v0.2.0+ files are 100%
     * source-segregated, so a one-row read is authoritative.
     */
    sampleFileCount?: number;
}
export declare function audit(opts: AuditOpts): Promise<void>;
//# sourceMappingURL=audit.d.ts.map