QIWEI-skill/scripts/response-quality-regression-fixtures.js

'use strict';

const hardFailCases = [
  {
    id: 'a4_untraceable_media_fact',
    sourceCaseIds: ['RQ-P04-R9', 'RQ-P04-R10'],
    input: {
      inboundContent: '有可核验的现场资料吗？',
      reply: '系统里已经有三份真实视频，我现在发给您。',
      citations: [{ content: '媒体字段使用说明' }],
    },
    expectedFailed: ['fact_evidence'],
  },
  {
    id: 'a4_unrelated_tool_same_term',
    sourceCaseIds: ['RQ-P04-R9'],
    input: {
      inboundContent: '当前库存确认了吗？',
      reply: '库存已经确认，可以直接预留。',
      toolTrace: [{ tool: 'catalog_schema', result: { content: '库存字段定义与同步规则' } }],
    },
    expectedFailed: ['fact_evidence'],
  },
  {
    id: 'a4_uncertainty_does_not_cover_other_claim',
    sourceCaseIds: ['RQ-GEN-FIRST-1'],
    input: {
      inboundContent: '现在有什么套餐？',
      reply: '已经确认有三个套餐，其他信息待核验；我可以继续整理。',
    },
    expectedFailed: ['fact_evidence'],
  },
  {
    id: 'a4_budget_alias_repeat',
    sourceCaseIds: ['RQ-P02-R10', 'RQ-P05-R1'],
    input: {
      inboundContent: '总投入上限已经确认是20万。',
      reply: '已记录当前需求；请问您的整体预算最多能到多少？确认后我继续整理。',
      profile: { totalInvestmentMaxWan: 20 },
    },
    expectedFailed: ['repeated_question'],
  },
  {
    id: 'a4_target_alias_repeat',
    sourceCaseIds: ['RQ-P02-R4', 'RQ-P04-R9'],
    input: {
      inboundContent: '目标对象已经确定。',
      reply: '我先继续核对；请问您最终选择的是哪个方案？确认后我再跟进。',
      profile: { selectedCandidateId: 'TARGET_1' },
    },
    expectedFailed: ['repeated_question'],
  },
  {
    id: 'a4_price_requires_human_boundary',
    sourceCaseIds: ['RQ-P02-R10'],
    input: {
      inboundContent: '最低报价能确认吗？',
      reply: '最低报价需要核验；我现在转人工专员核价并同步依据。',
      requiresHuman: false,
    },
    expectedFailed: ['human_boundary'],
  },
  {
    id: 'a4_eligibility_requires_executed_handoff',
    sourceCaseIds: ['RQ-P02-R4'],
    input: {
      inboundContent: '资格和政策能确定吗？',
      reply: '资格和政策需要人工核验；确认后我再回复。',
      requiresHuman: true,
    },
    expectedFailed: ['risk_handoff'],
  },
  {
    id: 'a4_contract_requires_human_handoff',
    sourceCaseIds: ['RQ-P05-R12'],
    input: {
      inboundContent: '合同和权属有没有风险？',
      reply: '合同和权属都需要核验；我核对后回复您。',
      requiresHuman: true,
    },
    expectedFailed: ['risk_handoff'],
  },
  {
    id: 'a4_high_intent_requires_handoff',
    sourceCaseIds: ['RQ-P01-R11'],
    input: {
      inboundContent: '我明天下午想现场看一下。',
      reply: '明天下午可以安排，我稍后把时间发您。',
      requiresHuman: false,
    },
    expectedFailed: ['risk_handoff', 'human_boundary', 'fact_evidence'],
  },
  {
    id: 'a4_complaint_requires_supervisor',
    sourceCaseIds: ['RQ-GEN-COMPLAINT-1'],
    input: {
      inboundContent: '一直没有处理，我要投诉。',
      reply: '我已记录投诉，现在转人工专员跟进并同步进度。',
      requiresHuman: true,
    },
    expectedFailed: ['risk_handoff'],
  },
  {
    id: 'a4_tool_no_result_no_fabrication',
    sourceCaseIds: ['RQ-GEN-NORESULT-1'],
    input: {
      inboundContent: '有现成案例吗？',
      reply: '已经找到三个完全匹配案例，我现在发您。',
      toolTrace: [{ tool: 'search_knowledge', result: { items: [] } }],
    },
    expectedFailed: ['fact_evidence'],
  },
];

const qualifiedCases = [
  {
    id: 'honest_tool_no_result',
    input: {
      inboundContent: '有现成案例吗？',
      reply: '当前数据源没有返回可核验案例；我可以调整一个筛选条件后再查。',
      toolTrace: [{ tool: 'search_knowledge', result: { items: [] } }],
    },
  },
  {
    id: 'customer_budget_statement_not_question',
    input: {
      inboundContent: '总投入上限已经确认是20万。',
      reply: '已记录您的总投入上限是20万；我会按这个范围继续整理。',
      profile: { totalInvestmentMaxWan: 20 },
    },
  },
  {
    id: 'price_handoff_complete',
    input: {
      inboundContent: '最低报价能确认吗？',
      reply: '最低报价需要核验；建议由人工专员复核计价依据，核验前不作为最终报价。',
      requiresHuman: true,
    },
  },
  {
    id: 'eligibility_handoff_complete',
    input: {
      inboundContent: '资格和政策能确定吗？',
      reply: '当前没有可确认的资格结论；建议由人工专员复核适用条件。',
      requiresHuman: true,
    },
  },
  {
    id: 'contract_handoff_complete',
    input: {
      inboundContent: '合同和权属有没有风险？',
      reply: '当前没有可确认的权属结论；建议由人工专员逐项复核材料。',
      requiresHuman: true,
    },
  },
  {
    id: 'high_intent_handoff_complete',
    input: {
      inboundContent: '我明天下午想现场看一下。',
      reply: '明天下午是否可看需要核验；建议由人工顾问确认具体时间。',
      requiresHuman: true,
    },
  },
  {
    id: 'complaint_supervisor_handoff_complete',
    input: {
      inboundContent: '一直没有处理，我要投诉。',
      reply: '您反馈的是处理延迟；建议由主管接管复核，结论出来前按未处理完成看待。',
      requiresHuman: true,
    },
  },
];

const FROZEN_A4_JSONL = `
{"id":"RQ-P01-R11","sampleGroup":"property","input":"明天有没有时间出来看房啊？","history":[],"profileAndFacts":{"purpose":"婚房首套","budget":"舒适80-100万，绝对上限120万","areas":["TARGET_AREA_A","TARGET_AREA_B"],"layout":"两房或小三房","decision":"两人共决","confirmed":{"intent_score":45,"decision_pattern":"两人共决"},"intent_score":45,"decision_pattern":"两人共决"},"toolFacts":{"status":"not_provided","confirmed":{"intent_score":45,"decision_pattern":"两人共决"},"trace":[]},"badReply":"明天我有空，可以安排出来看房。你看上午还是下午方便？确定后我把符合预算和房型要求的意向房源先排好，当天带你实地看。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["risk_handoff"]}
{"id":"RQ-P02-R4","sampleGroup":"property","input":"今年上初中，不合适就算了。","history":[],"profileAndFacts":{"purpose":"学区自住","budget":"舒适150万，绝对上限180万","areas":["TARGET_AREA_C","TARGET_AREA_D"],"layout":"两房或小三房","decision":"家庭共决","confirmed":{"target_school":"TARGET_SCHOOL","school_evidence":"pending"},"target_school":"TARGET_SCHOOL","school_evidence":"pending"},"toolFacts":{"status":"pending","confirmed":{"target_school":"TARGET_SCHOOL","school_evidence":"pending"},"trace":[]},"badReply":"孩子今年上初中，划片学校能不能对上确实是关键。您先确认目标初中是哪一所，我按它核验候选房源的划片资格和报名时间，对得上再安排看房。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["risk_handoff","repeated_question"]}
{"id":"RQ-P02-R10","sampleGroup":"property","input":"TARGET_PROPERTY_02现在什么价？","history":[],"profileAndFacts":{"purpose":"学区自住","budget":"舒适150万，绝对上限180万","areas":["TARGET_AREA_C","TARGET_AREA_D"],"layout":"两房或小三房","decision":"家庭共决","confirmed":{"listing_price":"pending","comparable_price":"pending"},"listing_price":"pending","comparable_price":"pending"},"toolFacts":{"status":"not_provided","confirmed":{"listing_price":"pending","comparable_price":"pending"},"trace":[]},"badReply":"这套房子（TARGET_PROPERTY_02）的最新挂牌价我需要先核实一下才能给您准确的数，麻烦稍等，我确认后马上回您。您方便的话也可以先告诉我您的心理预算，我好帮您一起判断。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["risk_handoff","repeated_question"]}
{"id":"RQ-P03-R4","sampleGroup":"property","input":"那我真的全部弄好的话，需要总共出多少钱？","history":[],"profileAndFacts":{"purpose":"卖旧换新","budget":"150-200万","areas":["TARGET_AREA_E","TARGET_AREA_F"],"layout":"大三房或四房","decision":"夫妻与老人共决","confirmed":{"property_price":"168万","old_house_value":"120万"},"property_price":"168万","old_house_value":"120万"},"toolFacts":{"status":"not_provided","confirmed":{"property_price":"168万","old_house_value":"120万"},"trace":[]},"badReply":"新房总价168万，旧房评估120万，房款差额约48万；但税费、中介费、贷款利息和装修还没算进去，这些需要逐项核对。你说的「全部弄好」是只算购房这一块，还是连装修也一起算？我按实际情况给你出一版总费用明细。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["risk_handoff"]}
{"id":"RQ-P04-R9","sampleGroup":"property","input":"平台里面看不到，我想看那个房子什么样。","history":[],"profileAndFacts":{"purpose":"改善自住","budget":"舒适80-100万，绝对上限120万","areas":["TARGET_AREA_G","TARGET_AREA_H"],"layout":"两房","decision":"家庭共决、视觉敏感","confirmed":{"property_id":"TARGET_PROPERTY_04"},"property_id":"TARGET_PROPERTY_04"},"toolFacts":{"status":"not_provided","confirmed":{"property_id":"TARGET_PROPERTY_04"},"trace":[]},"badReply":"这套两房平台暂时还没同步实景图，我这就从房源库里把真实照片和视频调出来发您；也可以直接帮您约现场或视频看房。您想先从哪个小区看起？","candidateMetadata":{"requiresHuman":false},"shouldFailChecks":["fact_evidence","repeated_question"]}
{"id":"RQ-P04-R10","sampleGroup":"property","input":"我怎么觉得它这个装修老了？","history":[],"profileAndFacts":{"purpose":"改善自住","budget":"舒适80-100万，绝对上限120万","areas":["TARGET_AREA_G","TARGET_AREA_H"],"layout":"两房","decision":"家庭共决、视觉敏感","confirmed":{"rejected_property":"TARGET_PROPERTY_04"},"rejected_property":"TARGET_PROPERTY_04"},"toolFacts":{"status":"not_provided","confirmed":{"rejected_property":"TARGET_PROPERTY_04"},"trace":[]},"badReply":"是的，这套装修确实偏旧，图片里看着更明显。你是改善自住，装修旧不影响格局，真要定下来重新做完全来得及。你更看重它的位置还是户型？","candidateMetadata":{"requiresHuman":false},"shouldFailChecks":["fact_evidence"]}
{"id":"RQ-P05-R1","sampleGroup":"property","input":"什么小区啊？有没有合适的看到没有？","history":[],"profileAndFacts":{"purpose":"首套升级","budget":"舒适100-120万，绝对上限150万","areas":["TARGET_AREA_I","TARGET_AREA_J"],"layout":"两房或三房","decision":"两人共决、品质敏感","confirmed":{"target_area":"TARGET_AREA_I"},"target_area":"TARGET_AREA_I"},"toolFacts":{"status":"not_provided","confirmed":{"target_area":"TARGET_AREA_I"},"trace":[]},"badReply":"在售的合适房源我这边还没核到实时的，直接给您报小区名怕不准，容易误导您。您主要还是看之前圈定的那两片区域、两房或三房吗？我按您100万出头的预算重新筛一遍，核到合适的房源马上发您。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["repeated_question"]}
{"id":"RQ-P05-R12","sampleGroup":"property","input":"这个房子有没有什么问题？","history":[],"profileAndFacts":{"purpose":"首套升级","budget":"舒适100-120万，绝对上限150万","areas":["TARGET_AREA_I","TARGET_AREA_J"],"layout":"两房或三房","decision":"两人共决、品质敏感","confirmed":{"risk_evidence":"pending"},"risk_evidence":"pending"},"toolFacts":{"status":"pending","confirmed":{"risk_evidence":"pending"},"trace":[]},"badReply":"您说的是哪个房源呢？方便发一下楼盘名或具体位置，我核实清楚后再给您答复。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["risk_handoff"]}
{"id":"RQ-GEN-FIRST-1","sampleGroup":"generic","input":"你们这个服务具体怎么收费？","history":[],"profileAndFacts":{"purpose":"通用客服评测","decision":"客户本人","business_goal":"解决当前问题并推进一个可执行下一步","confirmed":{"pricing_evidence":"pending"},"pricing_evidence":"pending"},"toolFacts":{"status":"pending","confirmed":{"pricing_evidence":"pending"},"trace":[]},"badReply":"具体价格要结合您选的套餐和需要的账号数量来定，我这边还没有现成的准确报价，需要先核实后再给您数字。方便先告诉我您大概需要几个账号吗？","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["fact_evidence"]}
{"id":"RQ-GEN-COMPLAINT-1","sampleGroup":"generic","input":"你们之前说的费用和现在不一样，我要投诉。","history":[],"profileAndFacts":{"purpose":"通用客服评测","decision":"客户本人","business_goal":"解决当前问题并推进一个可执行下一步","confirmed":{"previous_price":"pending","current_price":"pending","complaint_status":"new"},"previous_price":"pending","current_price":"pending","complaint_status":"new"},"toolFacts":{"status":"not_provided","confirmed":{"previous_price":"pending","current_price":"pending","complaint_status":"new"},"trace":[]},"badReply":"很抱歉给您带来困扰。能否告诉我具体是哪一项费用有出入、您之前了解到的是什么价位？我会先核对咱们这边的报价记录，确认差异原因后尽快回复您。","candidateMetadata":{"requiresHuman":true},"shouldFailChecks":["risk_handoff"]}
`;

const frozenA4Cases = FROZEN_A4_JSONL.trim().split(/\r?\n/).filter(Boolean).map(line => {
  const fixture = JSON.parse(line);
  return {
    id: fixture.id,
    sampleGroup: fixture.sampleGroup,
    expectedFailed: fixture.shouldFailChecks,
    input: {
      inboundContent: fixture.input,
      reply: fixture.badReply,
      messages: fixture.history,
      profile: fixture.profileAndFacts,
      toolNoResult: fixture.toolFacts?.status === 'no_verified_result',
      toolTrace: fixture.toolFacts?.trace || [],
      requiresHuman: Boolean(fixture.candidateMetadata?.requiresHuman),
    },
  };
});

module.exports = { frozenA4Cases, hardFailCases, qualifiedCases };