hyreal-gen-pic/server/agent/provenance.js

'use strict';

/**
 * 智能问数智能体 · 数字溯源 post-check
 * ----------------------------------------------------------------------------
 * final 返回后的零 token 规则校验（turn-assessment 同哲学）：从回答文本抽取数值，
 * 逐一在本次运行工具结果的数值集合中做容差匹配；匹配不到的记为「未溯源」并随
 * 运行留痕展示（警示不阻断）。换算形态自动覆盖：百分比显示值（8.21 vs 0.0821）、
 * 万元/亿元换算（4.2万 vs 42000）。日期、TopN、题干序号等模式先行剔除降噪。
 */

function stripNoise(text) {
  return String(text || '')
    .replace(/\d{4}-\d{1,2}-\d{1,2}/g, ' ')   // 2026-10-01
    .replace(/\b\d{8}\b/g, ' ')                // 20261001
    .replace(/top\s*\d+/gi, ' ')               // Top5
    .replace(/turn\s*\d+/gi, ' ')              // Turn 2
    .replace(/v\d+/gi, ' ');                   // verdict 引用 v3
}

function extractNumbers(text) {
  const out = [];
  const re = /-?\d+(?:,\d{3})*(?:\.\d+)?/g;
  const cleaned = stripNoise(text);
  let m;
  while ((m = re.exec(cleaned))) {
    const n = Number(m[0].replace(/,/g, ''));
    if (Number.isFinite(n)) out.push(n);
  }
  return out;
}

/** 递归收集工具产物里的数值（深度/广度有界，防大产物拖慢） */
function collectFromData(data, into, depth = 0) {
  if (data == null || typeof data !== 'object' || depth > 4) return;
  if (Array.isArray(data)) {
    for (const item of data.slice(0, 60)) collectFromData(item, into, depth + 1);
    return;
  }
  for (const v of Object.values(data)) {
    if (typeof v === 'number' && Number.isFinite(v)) into.push(v);
    else if (v && typeof v === 'object') collectFromData(v, into, depth + 1);
  }
}

function collectCandidates(steps) {
  const cands = [];
  for (const step of steps || []) {
    if (step.type !== 'tool' || !step.ok) continue;
    collectFromData(step.data, cands);
    for (const n of extractNumbers(step.summary || '')) cands.push(n);
  }
  return cands;
}

function matches(cands, n) {
  return cands.some((c) => {
    if (Math.abs(c - n) <= Math.max(Math.abs(c) * 0.005, 0.01)) return true;
    // 展示换算：百分比（×100）、万元（×1e4）、亿元（×1e8），以及反向
    for (const k of [100, 1e4, 1e8]) {
      if (Math.abs(c - n * k) <= Math.max(Math.abs(c) * 0.005, 0.01)) return true;
      if (Math.abs(c * k - n) <= Math.max(Math.abs(n) * 0.005, 0.01)) return true;
    }
    return false;
  });
}

/**
 * @returns {{total:number, untraced:number[], ratio:number}}
 */
function checkProvenance(answer, steps) {
  const nums = extractNumbers(answer);
  if (!nums.length) return { total: 0, untraced: [], ratio: 1 };
  const cands = collectCandidates(steps);
  if (!cands.length) return { total: nums.length, untraced: nums.slice(0, 12), ratio: 0 };
  const untraced = [];
  for (const n of nums) {
    if (!matches(cands, n)) untraced.push(n);
  }
  return { total: nums.length, untraced: untraced.slice(0, 12), ratio: nums.length ? 1 - untraced.length / nums.length : 1 };
}

module.exports = { extractNumbers, collectCandidates, checkProvenance };