import type { EvolutionProposal, EvolutionVerdict, IndependentEvaluatorResult, RegressionSkepticResult } from './evolution-types.js';
import { type EvaluationPackage } from './independent-evaluator-runner.js';
/**
 *
 * The regression skeptic is a SEPARATE sub-agent (independent of
 * the author AND the independent evaluator). Its job is to
 * REFUTE the proposal — find drift, overfit, and safety
 * regression risks. A `blocker` field is a hard revert signal:
 * the proposal cannot be promoted while a blocker stands.
 *
 * Inputs:
 *   - The same evaluation package the scorer sees
 *     (target_kind / target_release_id / optimization_dimension /
 *     before_snapshot / after_snapshot / diff / rubric /
 *     red_lines / source_traces).
 *   - The proposal verdict (from the post-evaluator aggregation).
 *   - The independent evaluator's result.
 *
 * Output: RegressionSkepticResult { driftRisks, overfitRisks,
 * safetyRegressionRisks, blocker? }.
 *
 * M4 ships a deterministic default skeptic that does NOT call an
 * LLM. The real LLM-backed skeptic lands in M5; the M4 unit tests
 * exercise the contract via a stub `invokeLlm` factory.
 */
/**
 * Optional LLM call factory for the skeptic. The default
 * implementation (`deterministicInvokeSkepticLlm`) is fully
 * deterministic; tests can swap in a stub.
 */
export type SkepticLlmInvoke = (pkg: EvaluationPackage, prompt: string) => Promise<RegressionSkepticResult>;
/**
 * Build the prompt handed to the skeptic LLM. By construction
 * this contains the SAME evaluation package the scorer saw
 * (independent context: separate call, separate model, separate
 * session), the proposal verdict, and the evaluator's result.
 */
export declare function buildSkepticPrompt(pkg: EvaluationPackage, verdict: EvolutionVerdict, evaluatorResult: IndependentEvaluatorResult): string;
/**
 * Default skeptic LLM call: deterministic, no LLM dependency.
 *
 * The default skeptic looks for three classes of risk:
 *   1. Drift: any red_line that is NEW in the after_snapshot and
 *      not present in the before_snapshot.
 *   2. Overfit: the diff mentions a tight `prompt_template` change
 *      without an accompanying rubric entry (proxy for prompt
 *      inflation).
 *   3. Safety regression: any red_line that the author DROPPED
 *      from the after_snapshot.
 *
 * The skeptic emits a `blocker` when (a) the evaluator's score
 * is below the after_score the author claimed AND a red_line
 * was dropped, or (b) the red_lines count grew by more than 0
 * (a "red line added" is treated as drift, not a hard blocker).
 */
export declare const deterministicInvokeSkepticLlm: SkepticLlmInvoke;
/**
 * Public entry point: run the regression skeptic against the
 * evaluation package, the proposal verdict, and the independent
 * evaluator's result. The skeptic is a SEPARATE sub-agent call:
 * it does NOT share a context with the evaluator or the author.
 */
export declare function runRegressionSkeptic(proposal: EvolutionProposal, verdict: EvolutionVerdict, evaluatorResult: IndependentEvaluatorResult, invokeLlm?: SkepticLlmInvoke): Promise<RegressionSkepticResult>;