export interface HarvestPattern {
    id: string;
    name?: string;
    content?: string;
}
export interface HarvestedTask {
    id: string;
    input: {
        id: string;
        q: string;
        targetId: string;
    };
    expected: string;
    provenanceTier: 'oracle:self-identity';
}
export interface BlendedCorpus {
    version: string;
    corpusHash: string;
    anchorIds: string[];
    tasks: Array<{
        id: string;
        input: unknown;
        expected: unknown;
    }>;
}
/**
 * Harvest up to `sample` self-retrieval tasks from real patterns. Deterministic
 * stride sampling (stable across runs); skips docs whose body is too thin to
 * form a discriminative query.
 */
export declare function harvestSelfSupervisedTasks(patterns: HarvestPattern[], opts?: {
    sample?: number;
    minQueryTerms?: number;
}): HarvestedTask[];
/** Content hash over the task ids+queries — changes iff the corpus changes. */
export declare function hashBlend(tasks: Array<{
    id: string;
    input: unknown;
    expected: unknown;
}>): string;
/**
 * Blend a human-labeled anchor set with harvested tasks into one versioned,
 * hashed corpus. The version encodes the sizes + hash so it visibly grows as the
 * store does; `anchorIds` marks the never-regress subset.
 */
export declare function blendCorpus(anchor: Array<{
    id: string;
    input: unknown;
    expected: unknown;
}>, harvested: HarvestedTask[]): BlendedCorpus;
//# sourceMappingURL=harness-corpus-harvester.d.ts.map