/**
 * Heuristic quality/coverage analyzer for sharegpt dataset JSONL files
 * (Dataset-uploader.md §3.1 — the `dataset_analyze` tool's core).
 *
 * Pure read-only analysis: no files are modified. The report is a plain
 * object the extension renders as markdown so the agent can decide whether
 * the dataset is worth cleaning/uploading.
 *
 * Report contents:
 *   - total samples + malformed line count
 *   - length distribution (p50/p95 chars per sample, rough token est chars/4)
 *   - per-tool coverage: how many samples use each function_call tool name,
 *     flagged when below LOW_TOOL_COVERAGE_THRESHOLD samples
 *   - local duplicates: canonicalized-JSON hash (sorted keys), dup count
 *   - dry-run scrub residue: per-kind redaction counts over all samples —
 *     this is the "residue red flag": > 0 means the dataset MUST go through
 *     `dataset_clean` before upload
 *   - quality flags: samples with 0 tool calls, samples with an observation
 *     longer than LONG_OBSERVATION_CHARS
 */
/** Tools with fewer samples than this get flagged in the coverage table. */
export declare const LOW_TOOL_COVERAGE_THRESHOLD = 20;
/** Observations longer than this are flagged as oversized. */
export declare const LONG_OBSERVATION_CHARS = 8000;
/** Rough token estimate divisor (chars / 4). */
export declare const TOKEN_ESTIMATE_DIVISOR = 4;
export interface ToolCoverageEntry {
    tool: string;
    /** Number of samples containing at least one function_call for this tool. */
    samples: number;
    /** True when samples < LOW_TOOL_COVERAGE_THRESHOLD. */
    low: boolean;
}
export interface DatasetAnalysisReport {
    inputPath: string;
    totalSamples: number;
    malformedLines: number;
    lengthDistribution: {
        p50Chars: number;
        p95Chars: number;
        p50EstTokens: number;
        p95EstTokens: number;
    };
    /** Per-tool sample coverage, sorted by samples desc, then name. */
    toolCoverage: ToolCoverageEntry[];
    duplicates: {
        total: number;
        unique: number;
        /** total - unique (samples that are exact canonicalized duplicates). */
        duplicateSamples: number;
    };
    /**
     * Dry-run scrub over every sample: how many redactions the scrubber WOULD
     * make. Any total > 0 is the residue red flag — run dataset_clean first.
     */
    scrubResidue: {
        totalRedactions: number;
        byKind: Record<string, number>;
    };
    qualityFlags: {
        /** Samples with zero function_call entries. */
        zeroToolCalls: number;
        /** Samples containing an observation longer than LONG_OBSERVATION_CHARS. */
        longObservations: number;
    };
}
export interface LoadedJsonl {
    samples: unknown[];
    malformedLines: number;
}
/**
 * Load a JSONL file into parsed values, skipping (and counting) malformed
 * lines. Non-object JSON (e.g. a bare string) counts as malformed too.
 */
export declare function loadJsonl(inputPath: string): LoadedJsonl;
/**
 * Total character count of a sharegpt sample: all conversation entry values
 * plus the system prompt (when present). Used for length distribution,
 * maxSampleChars filtering, and token estimates.
 */
export declare function sampleChars(sample: Record<string, unknown>): number;
/** Tool names used by a sample's function_call entries (unique, in order). */
export declare function sampleToolNames(sample: Record<string, unknown>): string[];
/**
 * Canonicalize a JSON value: recursively sort object keys, drop undefined,
 * then stringify. Deterministic for duplicate detection.
 */
export declare function canonicalizeJson(value: unknown): string;
/**
 * Analyze a sharegpt dataset JSONL file. Read-only; never throws on
 * malformed lines (they are counted instead). Throws only when the input
 * file itself cannot be read.
 *
 * `options.extraValues` (same opaque values `dataset_clean` scrubs with —
 * secret-store + .env values) extends the dry-run scrub residue counts;
 * values are never printed.
 */
export declare function analyzeDataset(inputPath: string, options?: {
    extraValues?: string[];
}): DatasetAnalysisReport;
/** Render an analysis report as a markdown table the agent can read. */
export declare function renderAnalysisMarkdown(report: DatasetAnalysisReport): string;
//# sourceMappingURL=analyzer.d.ts.map