/**
 * LLM-judge scoring for dsh-eval: builds a judging prompt from the case and
 * its trace, calls an injected chat seam, and parses the model's strict-JSON
 * verdict into a final-answer score and hallucination flag. The production
 * seam wraps the dsh-llm stream API; tests inject a fake so the suite stays
 * keyless.
 *
 * @module dsh-eval/judge
 */
import { type LlmRuntime } from '@deepseek-ai/dsh-llm';
import type { BenchmarkCase, BenchmarkJudge, EvalJudgeVerdict, EvalTrace } from './types.ts';
/** One judge chat call: system instructions plus the single task prompt. */
export interface JudgeChatRequest {
    /** Provider route, e.g. `deepseek`. */
    provider: string;
    /** Judge model id. */
    model: string;
    /** System instructions demanding strict JSON output. */
    system: string;
    /** The task and trace summary to judge. */
    prompt: string;
}
/** The injected chat seam; returns the model's raw text reply. */
export type JudgeChat = (request: JudgeChatRequest) => Promise<string>;
/**
 * Summarize a trace for the judge: final assistant answer, the distinct tool
 * names called, and the failure counters a hallucination call needs.
 * @param trace - the merged trial trace.
 * @returns a compact human-readable summary.
 */
export declare function summarizeTrace(trace: EvalTrace): string;
/**
 * Build the judge's system instructions and task prompt.
 * @param caseValue - the benchmark case being judged.
 * @param trace - the merged trial trace.
 * @param judge - the judge configuration.
 * @returns the system and prompt texts.
 */
export declare function buildJudgePrompt(caseValue: BenchmarkCase, trace: EvalTrace, judge: BenchmarkJudge): {
    system: string;
    prompt: string;
};
/**
 * Parse the judge model's strict-JSON reply into a verdict. Unusable output
 * yields null fields, never a fabricated verdict.
 * @param text - the raw model reply.
 * @param maxScore - the configured maximum score.
 * @returns the parsed verdict.
 */
export declare function parseJudgeVerdict(text: string, maxScore: number): EvalJudgeVerdict;
/**
 * Judge one trial through the chat seam.
 * @param caseValue - the benchmark case being judged.
 * @param trace - the merged trial trace.
 * @param judge - the judge configuration.
 * @param chat - the injected chat seam.
 * @returns the parsed verdict; a chat failure rejects.
 */
export declare function judgeTrial(caseValue: BenchmarkCase, trace: EvalTrace, judge: BenchmarkJudge, chat: JudgeChat): Promise<EvalJudgeVerdict>;
/**
 * Judge one trial, converting a chat failure into an all-null verdict so a
 * judge outage reads as unjudged rather than a failed trial.
 * @param caseValue - the benchmark case being judged.
 * @param trace - the merged trial trace.
 * @param judge - the judge configuration.
 * @param chat - the injected chat seam.
 * @returns the parsed verdict, or all-null when the chat call threw.
 */
export declare function tryJudgeTrial(caseValue: BenchmarkCase, trace: EvalTrace, judge: BenchmarkJudge, chat: JudgeChat): Promise<EvalJudgeVerdict>;
/**
 * Build the production chat seam over a dsh-llm stream: one user turn, zero
 * temperature, and text-block assembly of the reply.
 * @param stream - the llm service's stream method.
 * @returns a chat seam reading only text blocks from the stream.
 */
export declare function llmJudgeChat(stream: LlmRuntime['stream']): JudgeChat;