/**
 * V3 CLI gaia-bench Command — ADR-133-PR8 + ADR-135 Tracks A/B/D/E/Q + ADR-136 Track Q
 *
 * Runs GAIA benchmark questions through the claude-flow agent loop and
 * reports pass-rate, cost, and per-question results.
 *
 * Contract (matches gaia-benchmark.yml workflow expectations):
 *   node bin/cli.js gaia-bench run \
 *     --level <1|2|3> \
 *     --limit <N> \
 *     --models <csv> \
 *     --output json
 *
 * JSON output shape:
 *   {
 *     level: number,
 *     model: string,
 *     summary: { total, passed, passRate, estCostUsd, hardnessDist? },
 *     results: [{ task_id, question, model, correct, answer, expected_output, error }]
 *   }
 *
 * Integration (iter 39 — ADR-135):
 *   Wires standalone track modules into the CLI so they are usable end-to-end.
 *   - Track A  (--voting-attempts N)   : multi-attempt self-consistency voting
 *   - Track B  (--planning-interval N) : periodic planning checkpoints in gaia-agent
 *   - Track D  (--enable-critic)       : adversarial critic review after agent answer
 *   - Track E  (--decompose)           : question decomposition for multi-step Qs
 *   - Track Q  (--hardness-routing)    : hardness-based compute allocation
 *
 * Precedence when flags combine:
 *   --hardness-routing overrides --max-turns and --voting-attempts per question.
 *   --voting-attempts > 1 takes precedence over --enable-critic (cost containment).
 *   --decompose works independently; sub-question answers feed into voting/critic/plain.
 *
 * Refs: ADR-133, ADR-135, ADR-136, #2165, iter 28/34/36/37/39
 */
import type { Command } from '../types.js';
export declare const gaiaBenchCommand: Command;
export default gaiaBenchCommand;
//# sourceMappingURL=gaia-bench.d.ts.map