// PreferenceSample — entry in exports/preference/chosen_rejected.jsonl.
// Source: real disagreements (audit_discrepancies, scrum ladder retries).
// Validator pins: chosen != rejected, both source_run_ids present, reason
// is non-empty. No synthesized preferences.
import {
  ValidationResult, requireString, requireIsoTimestamp, requireProvenance,
} from "./types";

export const PREFERENCE_SAMPLE_SCHEMA_VERSION = 1;

export interface PreferenceSample {
  schema_version: number;
  id: string;
  prompt: string;
  chosen: string;
  rejected: string;
  reason: string;                  // why chosen > rejected — must be non-empty
  chosen_run_id: string;
  rejected_run_id: string;
  created_at: string;
  provenance: { source_file: string; line_offset?: number; sig_hash: string; recorded_at: string };
}

export function validatePreferenceSample(input: unknown): ValidationResult<PreferenceSample> {
  const errors: string[] = [];
  if (typeof input !== "object" || input === null) return { valid: false, errors: ["expected object"] };
  const r = input as Record<string, unknown>;
  let ok = true;

  if (r.schema_version !== PREFERENCE_SAMPLE_SCHEMA_VERSION) {
    errors.push(`schema_version: expected ${PREFERENCE_SAMPLE_SCHEMA_VERSION}, got ${JSON.stringify(r.schema_version)}`);
    ok = false;
  }
  ok = requireString(r.id, "id", errors) && ok;
  ok = requireString(r.prompt, "prompt", errors) && ok;
  ok = requireString(r.chosen, "chosen", errors) && ok;
  ok = requireString(r.rejected, "rejected", errors) && ok;
  ok = requireString(r.reason, "reason", errors) && ok;
  ok = requireString(r.chosen_run_id, "chosen_run_id", errors) && ok;
  ok = requireString(r.rejected_run_id, "rejected_run_id", errors) && ok;
  ok = requireIsoTimestamp(r.created_at, "created_at", errors) && ok;
  ok = requireProvenance(r.provenance, "provenance", errors) && ok;

  // Self-pairing guard.
  if (r.chosen === r.rejected && typeof r.chosen === "string") {
    errors.push("chosen and rejected must differ — preference data needs a real disagreement");
    ok = false;
  }
  if (r.chosen_run_id === r.rejected_run_id && typeof r.chosen_run_id === "string") {
    errors.push("chosen_run_id and rejected_run_id must differ — same run can't disagree with itself");
    ok = false;
  }
  if (typeof r.reason === "string" && (r.reason as string).trim().length === 0) {
    errors.push("reason: must be non-whitespace (every preference needs WHY chosen > rejected)");
    ok = false;
  }

  if (!ok) return { valid: false, errors };
  return { valid: true, value: r as unknown as PreferenceSample };
}