/**
 * Benchmark runner for dsh-eval: one fresh subprocess per case x trial.
 *
 * Each trial owns a private temp directory with a copied workspace, an
 * isolated DSH_HOME, and a patch overlay that forces plain-JSONL persistence
 * and non-interactive workspace-scoped permissions. The spawned command is
 * the same trusted dsh harness (credentials flow through deliberately: the
 * child must reach the real model API, and the session log never stores
 * them), so the defensive scrubbed-env rule's leak concern does not apply to
 * this child. Timeout kills the direct child and reports timed-out orthogonally
 * from its exit code; Windows descendants of a killed process may survive.
 *
 * @module dsh-eval/runner
 */
import type { Benchmark, EvalRun } from './types.ts';
import { type JudgeChat } from './judge.ts';
/** Runtime overrides applied to a loaded benchmark. */
export interface RunOptions {
    /** Override the benchmark's dsh command argv. */
    command?: readonly string[];
    /** Override the benchmark's spawned profile. */
    profile?: string;
    /** Override the benchmark's trials per case. */
    trials?: number;
    /** Override the benchmark's in-flight trial limit. */
    concurrency?: number;
    /** Root for trial directories; defaults to the platform temp dir. */
    tempRoot?: string;
    /** LLM-judge chat seam; required when the benchmark configures a judge. */
    judgeChat?: JudgeChat;
}
/**
 * Run every case x trial through a bounded worker pool and aggregate the
 * completed trials.
 *
 * Trials are independent by construction — each owns a private temp directory,
 * workspace copy, and DSH_HOME — so the only thing serial execution buys is
 * determinism. The pool keeps that anyway: results land at their task index, so
 * the run record stays in case-then-trial order no matter how the workers
 * interleave. The first failure to escape `runCaseTrial` stops the remaining
 * workers and rejects the run, which is the same contract as the serial loop.
 *
 * @param benchmark - the loaded benchmark.
 * @param options - runtime overrides and test seams.
 * @returns the completed run record, written by the caller.
 */
export declare function runBenchmark(benchmark: Benchmark, options?: RunOptions): Promise<EvalRun>;