import { type FeaturePattern, type ParseError } from "@cosmicdrift/kumiko-framework/engine";
export type AuthoringStyle = "canonical" | "legacy";
export type CorpusWarning = {
    /** Repo-relative path to the file that triggered the warning. */
    readonly sourcePath: string;
    /** Human-readable explanation. Currently only "parser-throw" but
     *  kept open-ended so future builders can add more (e.g.
     *  "duplicate-id", "no-feature-name"). */
    readonly message: string;
};
export type FewShotEntry = {
    /** Stable id derived from the path (`samples/recipes/basic-entity`). */
    readonly id: string;
    /** Repo-relative path to the feature-file. */
    readonly sourcePath: string;
    /** Repo-relative path to the workspace package.json (for description lookup). */
    readonly packageJsonPath: string | undefined;
    /** Workspace name (`@cosmicdrift/kumiko-sample-basic-entity`). */
    readonly packageName: string | undefined;
    /** English description from package.json. */
    readonly description: string | undefined;
    /** Feature name from `defineFeature("...", ...)`. Undefined if the
     *  parser couldn't read it (rare — implies a non-feature file got
     *  picked up). */
    readonly featureName: string | undefined;
    /** Pattern-categories present in this feature, deduplicated. Useful
     *  as topic-tags for retrieval ("show me cross-cutting examples"). */
    readonly tags: readonly string[];
    /** Counts per pattern-kind — quick stats without scanning the
     *  patterns array. */
    readonly patternsByKind: Readonly<Record<string, number>>;
    /** All parsed patterns. Same shape the parser emits. */
    readonly patterns: readonly FeaturePattern[];
    /** Errors the parser raised. Empty for canonical-form features. */
    readonly parseErrors: readonly ParseError[];
    /** `canonical` (clean parse) or `legacy` (parser couldn't read it
     *  fully — Factory-style / identifier-refs). */
    readonly authoringStyle: AuthoringStyle;
    /** Raw source text — kept verbatim so the LLM can train on the
     *  exact byte-form, including comments + whitespace. */
    readonly rawSource: string;
};
export type FewShotCorpus = {
    /** ISO-instant when the corpus was generated. */
    readonly generatedAt: string;
    /** Total entry count, broken down by authoringStyle for quick stats. */
    readonly totals: {
        readonly all: number;
        readonly canonical: number;
        readonly legacy: number;
    };
    readonly entries: readonly FewShotEntry[];
    /** Files that were discovered but couldn't be turned into entries.
     *  Surfaces parser crashes + duplicate-id collisions instead of
     *  swallowing them — the regenerate-script reports these to the user
     *  and the drift-test asserts the count stays constant. */
    readonly warnings: readonly CorpusWarning[];
};
export type BuildFewShotCorpusOptions = {
    /** Repo root — used for relative-path output and security guards. */
    readonly repoRoot: string;
    /** Folders to scan recursively. Defaults to samples/* + bundled-features. */
    readonly scanRoots?: readonly string[];
};
export declare function buildFewShotCorpus(options: BuildFewShotCorpusOptions): FewShotCorpus;
/**
 * Stable id from the source path. Drops the leading `samples/` or
 * `packages/` prefix and the trailing `/src/feature.ts` suffix so the
 * id reads like the canonical short name (`basic-entity`,
 * `bundled-features/auth-email-password`).
 */
export declare function pathToId(sourcePath: string): string;