import type { ActionEntry } from "../agent/production-agent.js";
import type { AgentRunner } from "./agent-runner.js";
import type { AgentRunOutput, Eval, EvalProductionContext, EvalProductionIdentity, EvalResultRow, EvalRunReport } from "./types.js";
interface ScoreEvalOptions {
    thresholdOverride?: number;
    onRunOutput?: (output: AgentRunOutput) => void;
    /** Marks unbranded lower-level runners that use the production chat path. */
    productionPath?: boolean;
    /** Explicitly opts lower-level scoring into the non-production path. */
    nonProductionPath?: true;
}
export declare function scoreEval(evalCase: Eval, runner: AgentRunner, opts?: ScoreEvalOptions): Promise<EvalResultRow>;
export declare function runEvals(evals: Eval[], runner: AgentRunner, opts?: ScoreEvalOptions & {
    persist?: boolean;
}): Promise<EvalRunReport>;
export declare function discoverEvalFiles(root: string, pattern?: string): Promise<string[]>;
export declare function loadEvals(root: string, pattern?: string): Promise<{
    files: string[];
    evals: Eval[];
}>;
export interface RunEvalSuiteOptions {
    cwd?: string;
    pattern?: string;
    thresholdOverride?: number;
    actions?: Record<string, ActionEntry>;
    systemPrompt?: string;
    productionContext?: EvalProductionContext;
    identity?: EvalProductionIdentity;
    requireProductionChatPath?: boolean;
    /** Allows custom run callbacks with an injected lower-level runner. */
    nonProductionPath?: true;
    persist?: boolean;
    runner?: AgentRunner;
    evals?: Eval[];
}
export declare function runEvalSuite(opts?: RunEvalSuiteOptions): Promise<{
    report: EvalRunReport;
    files: string[];
}>;
export declare function loadProductionEvalContext(cwd: string, identity?: EvalProductionIdentity): Promise<EvalProductionContext>;
export {};