/**
 * segment.ts — Tier-A deterministic (no-model) segmenter.
 *
 * Splits a CLAUDE.md / AGENTS.md into ATOMIC candidate rules with provenance.
 * Pure, deterministic, strict TS, no external deps.
 *
 * Design bias: PRECISION over recall. A missed rule costs a row; a garbage
 * atom costs credibility. When in doubt we UNDER-split and REJECT.
 */
/** A single atomic candidate rule extracted from an instructions file. */
export interface SegmentedRule {
    /** Normalized rule text (bullet marker stripped, continuation joined, whitespace collapsed). */
    text: string;
    /** Source file path (as supplied by the caller), or undefined. */
    file: string | undefined;
    /** 1-based inclusive start line in the source. */
    lineStart: number;
    /** 1-based inclusive end line in the source. */
    lineEnd: number;
    /** Verbatim slice of the source spanning [lineStart..lineEnd] — for UI highlight. */
    exactQuote: string;
    /** 3/3 cues => "high"; 2/3 => "medium". (Rejected candidates are never emitted.) */
    confidence: "high" | "medium";
}
/** Why the segmenter decided a bullet is NOT a rule (the transparency signal —
 * see `research/rule-enforcer-design.md` §3). `index`/`description`/`leadin`/
 * `no-signal` come from the gate; `section` means it sits under a non-rule
 * heading (Setup / Commands / Key Files / Architecture …).
 *
 * `leadin` is a colon-terminated procedure/enumeration HEADER ("To add a
 * setting:", "Run the full test suite:", "Python check:") whose enforceable
 * content — if any — lives in the sub-bullets/code-block it introduces (verified
 * on the OSS corpus: the sub-items are segmented independently, so dropping the
 * header loses nothing). Kept DISTINCT from `no-signal` on purpose: routing
 * re-surfaces `no-signal` skips in the "possible (review)" recall tier, and a
 * lead-in is a CONFIDENT drop that must not re-enter that tier. */
export type RejectReason = "index" | "description" | "leadin" | "no-signal" | "section";
/** A BULLET the segmenter saw but did NOT treat as a rule, with the reason — so
 * the audit report can be honest about what it set aside (a heuristic misses
 * declarative rules; showing skips lets a human eyeball a wrong drop). Bounded to
 * list items on purpose; rejected paragraph prose is not reported (too noisy). */
export interface SkippedBullet {
    readonly text: string;
    readonly file: string | undefined;
    readonly lineStart: number;
    readonly lineEnd: number;
    readonly reason: RejectReason;
}
/** The segmenter's full output: the confident/medium candidate rules PLUS the
 * bullets it rejected (with reasons), so nothing is silently dropped. */
export interface SegmentResult {
    readonly segments: SegmentedRule[];
    readonly skipped: SkippedBullet[];
}
/**
 * Split a CLAUDE.md / AGENTS.md into atomic candidate rules with provenance.
 *
 * Deterministic Tier-A heuristic. Code fences and tables are excluded from
 * candidacy. Candidate units are (a) list items with attached continuation
 * lines and (b) sentences of paragraphs under a rule-ish heading. This function
 * is a thin DISPATCHER — each block type is handled by its own pure helper
 * (`handleListItem` / `handleParagraph`); the state it threads is the fence
 * toggle and the current `HeadingState`.
 */
export declare function segmentInstructions(markdown: string, file?: string, skipLines?: ReadonlySet<number>): SegmentResult;
//# sourceMappingURL=segment.d.ts.map