dsh-data-cleaning-agent 0.6.1 → 0.6.2

package/CHANGELOG.md

@@ -4,6 +4,15 @@
 
 ## [Unreleased]
 
+## [0.6.2] - 2026-09-04
+
+### Fixed
+- 清洗补全结果 CSV/XLSX 的插件字段与状态字段统一导出为中文表头，并按任务字段选择保留空值列，
+  不再因企查查未返回某一字段而从制品中静默丢列。
+- 将任务选择的补全字段贯穿中央工作台、Agent-owned 命令、G5 Host Bridge、任务恢复与耐久制品；
+  工商详情补充注册地址、行政区划、经营范围、行业、营业期限和企业规模映射，企业简介等画像字段按需
+  调用 `get_company_profile`，且不把未声明层级的“企查查行业”猜测为一级/二级行业。
+
 ## [0.6.1] - 2026-09-04
 
 ### Fixed

package/README.en.md

@@ -2,7 +2,7 @@
 
 > A data cleaning & completion agent plugin for DeepSeek Harness: local CSV/XLSX/JSON engine plus optional Qichacha (QCC) MCP enterprise-data enrichment. Initiated and maintained by the Qichacha (QCC) team.
 >
-> Current source version / 当前源码版本: **0.6.1** (stable release)
+> Current source version / 当前源码版本: **0.6.2** (stable release)
 
 [![CI](https://github.com/duhu2000/dsh-data-cleaning-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/duhu2000/dsh-data-cleaning-agent/actions/workflows/ci.yml)
 [![npm](https://img.shields.io/npm/v/dsh-data-cleaning-agent)](https://www.npmjs.com/package/dsh-data-cleaning-agent)
@@ -117,6 +117,8 @@ See [the Phase-3 acceptance record](docs/PHASE3-ACCEPTANCE.md) and
 See [the 0.5.1 release record](docs/RELEASE-0.5.1.md) for the README fix and release-text gate.
 See [the 0.5.2 release record](docs/RELEASE-0.5.2.md) for native DSH UI alignment, verification, and rollback.
 See [the 0.5.3 release record](docs/RELEASE-0.5.3.md) for the business landing view and prompt builder.
+See [the 0.6.2 release record](docs/RELEASE-0.6.2.md) for Chinese export headers,
+complete field-selection propagation, and profile-field enrichment.
 See [the 0.6.1 release record](docs/RELEASE-0.6.1.md) for the Agent-owned QCC workbench,
 session isolation, recovered statistics, and real end-to-end validation.
 See [the 0.6.0 release record](docs/RELEASE-0.6.0.md) for the taskId workflow, durable artifacts,

package/README.md

@@ -2,7 +2,7 @@
 
 > 在 DeepSeek Harness 中清洗、补全、画像企业名单数据的智能体插件：本地 CSV/XLSX/JSON 引擎 + 可选企查查（Qichacha/QCC）MCP 企业数据补全，由企查查（Qichacha/QCC）团队发起并维护。
 >
-> 当前源码版本 / Current source version: **0.6.1**（正式版本）
+> 当前源码版本 / Current source version: **0.6.2**（正式版本）
 
 [![CI](https://github.com/duhu2000/dsh-data-cleaning-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/duhu2000/dsh-data-cleaning-agent/actions/workflows/ci.yml)
 [![npm](https://img.shields.io/npm/v/dsh-data-cleaning-agent)](https://www.npmjs.com/package/dsh-data-cleaning-agent)
@@ -113,7 +113,8 @@ bash <(curl -fsSL https://raw.githubusercontent.com/duhu2000/dsh-data-cleaning-a
 0.5.1 文档补丁与防回归发布门见 [docs/RELEASE-0.5.1.md](docs/RELEASE-0.5.1.md)。
 0.5.2 DSH 原生 UI 对齐范围、验收与回滚见 [docs/RELEASE-0.5.2.md](docs/RELEASE-0.5.2.md)。
 0.5.3 业务首页、提示词生成和输入框下方流程栏见 [docs/RELEASE-0.5.3.md](docs/RELEASE-0.5.3.md)。
-0.6.1 Agent-owned QCC 工作台、会话隔离、恢复统计及真实闭环验收见
+0.6.2 中文导出表头、完整字段选择传递与画像字段补全见
+[docs/RELEASE-0.6.2.md](docs/RELEASE-0.6.2.md)。0.6.1 Agent-owned QCC 工作台、会话隔离、恢复统计及真实闭环验收见
 [docs/RELEASE-0.6.1.md](docs/RELEASE-0.6.1.md)。0.6.0 五步 taskId 工作流、耐久制品、
 跨重启恢复与双基线验收见 [docs/RELEASE-0.6.0.md](docs/RELEASE-0.6.0.md)。
 

package/docs/RELEASE-0.6.1.md

@@ -45,6 +45,20 @@
 
 ## 外部发布核验
 
-Tag 推送后必须确认 Release workflow 全绿、npm `latest=0.6.1`、provenance 存在、GitHub Release
-非 draft/非 prerelease，并从公共 Registry 在全新隔离目录安装验证。实际 workflow run、tarball
-哈希与公共安装结果将在发布完成后的仓库进度记录中补充。
+- PR [#3](https://github.com/duhu2000/dsh-data-cleaning-agent/pull/3) 四项 CI 全绿后合并；
+  `v0.6.1` 指向合并提交 `77a19aa`。
+- Release workflow [33880569564](https://github.com/duhu2000/dsh-data-cleaning-agent/actions/runs/33880569564)
+  全绿；版本校验、发布模式门禁、npm OIDC publish 与 GitHub Release 均成功。
+- npm `latest` 为 `0.6.1`；发布时间为 2026-09-04T13:53:39Z（北京时间 2026-09-04 21:53）。
+- tarball SHA-1：`ab9aaff6738e3ede08768138bc7a9000ccc28ed2`。
+- tarball integrity：
+  `sha512-VWsVelLCxpGYDZ1TZrxlZWLGC86IjtOJDZAszukCs5LaPwkos8UcJn0IWmYtdKF7S3a8TsQGN1KhOhDL0OCHFw==`。
+- npm Registry 返回 SLSA v1 provenance；隔离安装后的 `npm audit signatures` 验证 10 个 Registry
+  签名和 1 个 attestation。
+- 从公共 Registry 全新安装成功；包版本为 0.6.1，主入口可导入，浏览器 client 语法门通过，
+  `lib/qcc-command.js` 与本发布记录均存在。
+- DSH `0.1.1-rc.2` 全新隔离 Profile 安装 `dsh-data-cleaning-agent@0.6.1` 成功并加载 Host 插件。
+  第二个临时 Web Host 因本机全局文件监听资源耗尽（`EMFILE`）未完成 HTTP seam；未停止或改动用户
+  正在运行的 3080 实例。真实工作台闭环证据见上方「验收证据」。
+- GitHub Release [v0.6.1](https://github.com/duhu2000/dsh-data-cleaning-agent/releases/tag/v0.6.1)
+  已发布，为 Latest，非 draft、非 prerelease。

package/docs/RELEASE-0.6.2.md

@@ -0,0 +1,40 @@
+# 0.6.2 中文字段导出与完整补全字段修复
+
+> 版本：**0.6.2**
+> 发布日期：2026-09-04
+> 发布来源：`v0.6.2` Tag 触发 GitHub Actions，使用 npm OIDC Trusted Publishing。
+
+## 目标
+
+0.6.2 是 0.6.1 的结果正确性补丁，不扩大企查查工具域，修复真实任务中结果 XLSX 仅出现少量
+英文字段的问题：
+
+1. 任务选中的补全维度贯穿工作台、Agent-owned 命令、G5 Host Bridge、恢复/重试与耐久制品；
+2. CSV/XLSX 的插件补全字段和系统状态字段统一使用中文表头；
+3. 即使企查查未返回某个已选字段，结果文件也保留对应中文空列，不再静默丢列；
+4. 工商工具补充注册地址、行政区划、经营范围、行业、营业期限和企业规模映射；
+5. 企业简介及明确的一/二级行业字段按需调用 `get_company_profile`；未声明层级的“企查查行业”
+   不会被猜测填入一级或二级行业。
+
+## 兼容与调用边界
+
+- 稳定发布基线仍为 DSH `0.1.1-rc.2`；`0.1.2-alpha.2` 继续通过隔离 Bridge 兼容。
+- 只有选择企业简介、一级行业或二级行业时才增加企业画像调用，工作台调用估算同步调整。
+- QCC 继续采用 BYO 账号；插件不内置、不记录也不发布 OAuth token 或客户 Key。
+- 历史域、人员域和招投标域仍按既定范围延期，本补丁不新增相关工具。
+
+## 验收
+
+- 14 个目标维度按选择顺序完整进入结果数据和导出制品；
+- CSV/XLSX 表头为统一社会信用代码、登记状态、法定代表人、注册资本、成立日期、注册地址、
+  省份地区、城市、经营范围、一级行业、二级行业、营业期限、企业规模、企业简介；
+- 画像接口未明确返回层级时，一/二级行业保留空值而不是生成数据；
+- 未选择风险能力时不额外输出风险标签；
+- `npm run check` 全绿，176/176 自动化测试通过，npm dry-run 包内容命中白名单。
+
+## 升级与回滚
+
+- 升级：安装 `dsh-data-cleaning-agent@0.6.2` 并完全重启 DSH。
+- 回滚：重新安装 `dsh-data-cleaning-agent@0.6.1` 并完全重启 DSH。
+- 本补丁不修改 `dc_workflows_v2` 存储 schema，也不删除既有任务或工作区耐久制品。
+- 0.6.1 已生成的旧 XLSX 不会被自动重写；升级后重新生成制品即可获得中文完整表头。

package/lib/artifacts.js

@@ -7,6 +7,7 @@
  */
 import { createHash, randomUUID } from 'node:crypto';
 import XLSX from 'xlsx';
+import { FIELD_LABELS, normalizeFieldSelection } from './workflow-contract.js';
 
 const ROOT = '.dsh-data-cleaning-artifacts/v1';
 const MAX_ARTIFACT_BYTES = 32 * 1024 * 1024;
@@ -15,6 +16,17 @@ const MAX_ARTIFACT_BYTES = 32 * 1024 * 1024;
 const MAX_STORED_BYTES = Math.ceil(MAX_ARTIFACT_BYTES / 3) * 4 + 4;
 const SAFE_ID = /^(?:dcw|dca)-[a-zA-Z0-9-]{8,80}$/;
 
+const SYSTEM_FIELD_LABELS = Object.freeze({
+  biz_status: '经营状态',
+  risk_tags: '风险标签',
+  qcc_match_status: '匹配状态',
+  qcc_source: '数据来源',
+  qcc_error: '错误原因',
+  match_status: '匹配状态',
+  error: '错误原因',
+  _exception_reason: '异常原因',
+});
+
 export class ArtifactError extends Error {
   constructor(code, message, status = 400) {
     super(message);
@@ -44,10 +56,11 @@ function sha256(buffer) {
   return createHash('sha256').update(buffer).digest('hex');
 }
 
-function normalizeHeaders(headers, rows) {
+function normalizeHeaders(headers, rows, fieldSelection = []) {
   const fromInput = Array.isArray(headers) ? headers.map((item) => String(item ?? '').trim()).filter(Boolean) : [];
+  const selected = normalizeFieldSelection(fieldSelection);
   const discovered = [];
-  const seen = new Set(fromInput);
+  const seen = new Set([...fromInput, ...selected]);
   for (const row of rows) {
     for (const key of Object.keys(row ?? {})) {
       if (!seen.has(key)) {
@@ -56,7 +69,27 @@ function normalizeHeaders(headers, rows) {
       }
     }
   }
-  return [...fromInput, ...discovered].slice(0, 256);
+  return [...fromInput, ...selected.filter((field) => !fromInput.includes(field)), ...discovered].slice(0, 256);
+}
+
+function exportLabel(key) {
+  return FIELD_LABELS[key] ?? SYSTEM_FIELD_LABELS[key] ?? key;
+}
+
+function exportColumns(headers) {
+  const used = new Set();
+  return headers.map((key) => {
+    const base = exportLabel(key);
+    let label = base;
+    if (used.has(label)) {
+      const suffix = FIELD_LABELS[key] || SYSTEM_FIELD_LABELS[key] ? '（补全）' : '（原字段）';
+      label = `${base}${suffix}`;
+      let index = 2;
+      while (used.has(label)) label = `${base}${suffix.slice(0, -1)}${index++}）`;
+    }
+    used.add(label);
+    return { key, label };
+  });
 }
 
 function normalizeRows(value) {
@@ -104,8 +137,13 @@ export function deriveExceptionRows(rows) {
 
 function workbookBytes(rows, headers, sheetName) {
   const workbook = XLSX.utils.book_new();
-  const worksheet = XLSX.utils.json_to_sheet(rows, { header: headers, skipHeader: false });
-  worksheet['!cols'] = headers.map((header) => ({ wch: Math.min(42, Math.max(12, String(header).length * 2 + 4)) }));
+  const columns = exportColumns(headers);
+  const values = [
+    columns.map((column) => column.label),
+    ...rows.map((row) => columns.map((column) => row?.[column.key] ?? '')),
+  ];
+  const worksheet = XLSX.utils.aoa_to_sheet(values);
+  worksheet['!cols'] = columns.map((column) => ({ wch: Math.min(42, Math.max(12, String(column.label).length * 2 + 4)) }));
   XLSX.utils.book_append_sheet(workbook, worksheet, sheetName.slice(0, 31));
   workbook.Props = {
     Title: sheetName,
@@ -129,9 +167,10 @@ function csvBytes(rows, headers) {
     if (/^[\u0009\u000d\u000a ]*[=+\-@]/.test(text)) text = `'${text}`;
     return /[",\r\n]/.test(text) ? `"${text.replaceAll('"', '""')}"` : text;
   };
+  const columns = exportColumns(headers);
   const lines = [
-    headers.map(escapeCell).join(','),
-    ...rows.map((row) => headers.map((header) => escapeCell(row?.[header])).join(',')),
+    columns.map((column) => escapeCell(column.label)).join(','),
+    ...rows.map((row) => columns.map((column) => escapeCell(row?.[column.key])).join(',')),
   ];
   return Buffer.from(`\uFEFF${lines.join('\r\n')}`, 'utf8');
 }
@@ -180,7 +219,7 @@ export class WorkflowArtifactStore {
   async createBundle(taskId, input = {}) {
     assertId(taskId, 'taskId');
     const rows = normalizeRows(input.rows);
-    const headers = normalizeHeaders(input.headers, rows);
+    const headers = normalizeHeaders(input.headers, rows, input.fieldSelection);
     if (!headers.length) throw new ArtifactError('DC_ARTIFACT_HEADERS_REQUIRED', 'At least one export column is required.', 400);
     const exceptions = input.exceptionRows === undefined
       ? deriveExceptionRows(rows)

package/lib/client.js

@@ -2412,11 +2412,13 @@ window.__ModuleLoader__.load({
 
       const estimateQcc = async () => {
         const uniqueCompanies = new Set(runtime.rows.map((row) => String(row?.[nameField] ?? '').trim()).filter(Boolean)).size;
+        const requiresProfile = fieldSelection.some((field) => ['company_profile', 'industry_large', 'industry_middle'].includes(field));
+        const callsPerCompany = requiresProfile ? 3 : 2;
         actions.setQccEstimate({
           uniqueCompanies,
-          tools: ['主体查询', '工商信息'],
-          estimatedCalls: uniqueCompanies * 2,
-          maxCalls: 200,
+          tools: requiresProfile ? ['主体查询', '工商信息', '企业画像'] : ['主体查询', '工商信息'],
+          estimatedCalls: uniqueCompanies * callsPerCompany,
+          maxCalls: 300,
           withinLimit: runtime.rows.length <= 100,
           estimateType: 'upper-bound',
         });
@@ -2501,6 +2503,7 @@ window.__ModuleLoader__.load({
             rows: runtime.rows,
             headers: runtime.headers,
             nameField,
+            fieldSelection,
             includeRisk: false,
             concurrency: 2,
           });

package/lib/qcc-command.js

@@ -8,6 +8,7 @@
  */
 import { randomUUID } from 'node:crypto';
 import { QccBridgeError } from './qcc.js';
+import { normalizeFieldSelection } from './workflow-contract.js';
 
 export const TOOL_QCC_COMMAND = 'data_cleaning_qcc_run';
 
@@ -47,6 +48,7 @@ function normalizedInput(input = {}) {
       rows: clone(rows),
       headers: Array.isArray(input.headers) ? input.headers.map(String) : [],
       nameField: String(input.nameField ?? 'name'),
+      fieldSelection: normalizeFieldSelection(input.fieldSelection),
       includeRisk: input.includeRisk === true,
       concurrency: Math.min(4, Math.max(1, Math.trunc(Number(input.concurrency ?? 2)))),
     };
@@ -201,6 +203,7 @@ export class QccCommandStore {
     const result = await this.bridge.enrichRows(record.input.rows, {
       nameField: record.input.nameField,
       includeRisk: record.input.includeRisk,
+      fieldSelection: record.input.fieldSelection,
       concurrency: record.input.concurrency,
       maxRows: 100,
       execution,
@@ -210,6 +213,7 @@ export class QccCommandStore {
       headers: record.input.headers,
       nameField: record.input.nameField,
       includeRisk: record.input.includeRisk,
+      fieldSelection: record.input.fieldSelection,
       concurrency: record.input.concurrency,
       result,
       audit,

package/lib/qcc-runs.js

@@ -143,7 +143,7 @@ export class G5RunStore {
     return { value: await entry.promise, replayed: false };
   }
 
-  createRun({ headers, nameField, includeRisk, concurrency, result, audit = [] }) {
+  createRun({ headers, nameField, fieldSelection, includeRisk, concurrency, result, audit = [] }) {
     this.cleanup();
     const id = this.runIdFactory();
     const at = this.nowIso();
@@ -156,6 +156,7 @@ export class G5RunStore {
       touchedAtMs: this.clock(),
       headers: Array.isArray(headers) ? headers.map(String) : [],
       nameField: String(nameField ?? 'name'),
+      fieldSelection: Array.isArray(fieldSelection) ? fieldSelection.map(String) : [],
       includeRisk: Boolean(includeRisk),
       concurrency: Number(concurrency ?? 2),
       summary: clone(result.summary),
@@ -196,6 +197,7 @@ export class G5RunStore {
       createdAt: record.createdAt,
       updatedAt: record.updatedAt,
       headers: record.headers,
+      fieldSelection: record.fieldSelection,
       summary: record.summary,
       rows: record.rows,
       reviewQueue: record.reviewQueue,
@@ -269,6 +271,7 @@ export class G5RunStore {
       }, {
         ...options,
         includeRisk: record.includeRisk,
+        fieldSelection: record.fieldSelection,
         onAudit: (event) => this.appendAudit(record, event),
       });
       this.patchCompany(record, name, queued.rowIndexes, result);
@@ -303,6 +306,7 @@ export class G5RunStore {
           result = await bridge.enrichCompany(item.companyName, {
             ...options,
             includeRisk: record.includeRisk,
+            fieldSelection: record.fieldSelection,
             onAudit: (event) => this.appendAudit(record, event),
           });
         } catch (error) {

package/lib/qcc.js

@@ -24,6 +24,7 @@ export const QCC_TOOL_NAMES = Object.freeze({
   oauthStatus: 'qcc_oauth_status',
   entityLookup: 'mcp__qcc-company__get_company_by_query',
   registration: 'mcp__qcc-company__get_company_registration_info',
+  profile: 'mcp__qcc-company__get_company_profile',
   riskScan: 'mcp__qcc-risk__get_company_risk_scan',
 });
 
@@ -316,18 +317,98 @@ export function mapRegistrationFields(value, fallback = {}) {
   if (value.无匹配项 !== undefined) {
     throw new QccBridgeError('QCC_ENTITY_NOT_FOUND', 'Locked QCC entity could not be resolved by registration tool');
   }
+  const text = (...keys) => {
+    for (const key of keys) {
+      const item = value[key];
+      if (item !== undefined && item !== null && String(item).trim()) return String(item);
+    }
+    return '';
+  };
+  const region = text('所属地区', '所属地域', '地区');
+  const location = splitAdministrativeRegion(region);
   return {
-    credit_no: String(value.统一社会信用代码 ?? fallback.creditNo ?? ''),
-    legal_rep: String(value.法定代表人 ?? value.负责人 ?? value.经营者 ?? ''),
-    reg_capital: String(
-      value.注册资本 ?? value.注册资金 ?? value.开办资金 ?? value.成员出资总额 ?? value.资金数额 ?? '',
-    ),
-    establish_date: String(value.成立日期 ?? ''),
-    reg_status: String(value.登记状态 ?? value.执业状态 ?? value.证书状态 ?? ''),
-    biz_status: String(value.经营状态 ?? ''),
+    company_name: text('企业名称') || String(fallback.companyName ?? ''),
+    credit_no: text('统一社会信用代码', '信用代码') || String(fallback.creditNo ?? ''),
+    reg_no: text('工商注册号', '注册号'),
+    org_no: text('组织机构代码'),
+    reg_status: text('登记状态', '执业状态', '证书状态'),
+    legal_rep: text('法定代表人', '负责人', '经营者'),
+    reg_capital: text('注册资本', '注册资金', '开办资金', '成员出资总额', '资金数额'),
+    paid_capital: text('实缴资本'),
+    establish_date: text('成立日期'),
+    company_type: text('企业类型', '公司类型'),
+    registration_authority: text('登记机关'),
+    english_name: text('英文名', '英文名称'),
+    registered_address: text('注册地址', '住所', '经营场所'),
+    province: text('省份地区', '省份', '所属省份') || location.province,
+    city: text('城市', '所属城市', '市') || location.city,
+    district: text('区县', '所属区县') || location.district,
+    business_scope: text('经营范围'),
+    industry_category: text('国标行业'),
+    industry_large: text('一级行业', '企查查一级行业'),
+    industry_middle: text('二级行业', '企查查二级行业'),
+    operating_period: text('营业期限', '经营期限'),
+    company_size: text('企业规模', '人员规模'),
+    biz_status: text('经营状态'),
   };
 }
 
+function splitAdministrativeRegion(value) {
+  const region = String(value ?? '').trim().replace(/\s+/g, '');
+  if (!region) return { province: '', city: '', district: '' };
+  const municipality = region.match(/^((?:北京|上海|天津|重庆)市)(.*)$/);
+  if (municipality) {
+    const district = municipality[2].match(/^(.+?(?:区|县))/)?.[1] ?? '';
+    return { province: municipality[1], city: municipality[1], district };
+  }
+  const provinceMatch = region.match(/^(.+?(?:省|自治区|特别行政区))/);
+  const province = provinceMatch?.[1] ?? '';
+  const remainder = province ? region.slice(province.length) : region;
+  const city = remainder.match(/^(.+?(?:市|自治州|地区|盟))/)?.[1] ?? '';
+  const districtRemainder = city ? remainder.slice(city.length) : remainder;
+  const district = districtRemainder.match(/^(.+?(?:区|县|旗|市))/)?.[1] ?? '';
+  return { province, city, district };
+}
+
+export function mapProfileFields(value) {
+  if (!isRecord(value)) {
+    throw new QccBridgeError('QCC_CONTRACT_MISMATCH', 'QCC profile tool returned a non-object result');
+  }
+  if (value.无匹配项 !== undefined) return {};
+  return {
+    // “企查查行业”没有声明一/二级语义，不得猜测塞入层级列。
+    industry_large: String(value.一级行业 ?? value.企查查一级行业 ?? ''),
+    industry_middle: String(value.二级行业 ?? value.企查查二级行业 ?? ''),
+    company_profile: String(value.企业简介 ?? value.简介 ?? ''),
+  };
+}
+
+const LEGACY_ENRICHMENT_FIELDS = Object.freeze([
+  'credit_no', 'legal_rep', 'reg_capital', 'establish_date', 'reg_status', 'biz_status',
+]);
+const PROFILE_FIELDS = new Set(['industry_large', 'industry_middle', 'company_profile']);
+
+function requiresProfile(fieldSelection) {
+  return Array.isArray(fieldSelection) && fieldSelection.some((field) => PROFILE_FIELDS.has(field));
+}
+
+function mergeMappedFields(...sources) {
+  const output = {};
+  for (const source of sources) {
+    for (const [key, value] of Object.entries(source ?? {})) {
+      if (!Object.hasOwn(output, key) || (value !== '' && value !== null && value !== undefined)) output[key] = value;
+    }
+  }
+  return output;
+}
+
+function projectSelectedFields(fields, fieldSelection) {
+  const selected = Array.isArray(fieldSelection) && fieldSelection.length
+    ? [...new Set(fieldSelection.map(String))]
+    : LEGACY_ENRICHMENT_FIELDS;
+  return Object.fromEntries(selected.map((field) => [field, fields[field] ?? '']));
+}
+
 export function mapRiskTags(value) {
   if (!isRecord(value)) return '';
   const rows = Array.isArray(value.风险因子扫描) ? value.风险因子扫描 : [];
@@ -399,6 +480,7 @@ export class QccHostBridge {
       oauthStatus: this.has(QCC_TOOL_NAMES.oauthStatus),
       entityLookup: this.has(QCC_TOOL_NAMES.entityLookup),
       registration: this.has(QCC_TOOL_NAMES.registration),
+      profile: this.has(QCC_TOOL_NAMES.profile),
       riskScan: this.has(QCC_TOOL_NAMES.riskScan),
     };
     const ready = capabilities.entityLookup && capabilities.registration;
@@ -645,12 +727,15 @@ export class QccHostBridge {
       { searchKey: lockedKey },
       options,
     );
-    const fields = mapRegistrationFields(registration.data, match);
+    let mapped = mapRegistrationFields(registration.data, match);
+    if (requiresProfile(options.fieldSelection)) {
+      const profile = await this.call(QCC_TOOL_NAMES.profile, { searchKey: lockedKey }, options);
+      mapped = mergeMappedFields(mapped, mapProfileFields(profile.data));
+    }
+    const fields = projectSelectedFields(mapped, options.fieldSelection);
     if (options.includeRisk) {
       const risk = await this.call(QCC_TOOL_NAMES.riskScan, { searchKey: lockedKey }, options);
       fields.risk_tags = mapRiskTags(risk.data);
-    } else {
-      fields.risk_tags = '';
     }
     return {
       status: 'enriched',
@@ -670,12 +755,15 @@ export class QccHostBridge {
       { searchKey: creditNo },
       options,
     );
-    const fields = mapRegistrationFields(registration.data, { companyName, creditNo });
+    let mapped = mapRegistrationFields(registration.data, { companyName, creditNo });
+    if (requiresProfile(options.fieldSelection)) {
+      const profile = await this.call(QCC_TOOL_NAMES.profile, { searchKey: creditNo }, options);
+      mapped = mergeMappedFields(mapped, mapProfileFields(profile.data));
+    }
+    const fields = projectSelectedFields(mapped, options.fieldSelection);
     if (options.includeRisk) {
       const risk = await this.call(QCC_TOOL_NAMES.riskScan, { searchKey: creditNo }, options);
       fields.risk_tags = mapRiskTags(risk.data);
-    } else {
-      fields.risk_tags = '';
     }
     return { status: 'enriched', companyName, fields };
   }
@@ -690,6 +778,7 @@ export class QccHostBridge {
     }
 
     const requiredTools = [QCC_TOOL_NAMES.entityLookup, QCC_TOOL_NAMES.registration];
+    if (requiresProfile(options.fieldSelection)) requiredTools.push(QCC_TOOL_NAMES.profile);
     if (options.includeRisk) requiredTools.push(QCC_TOOL_NAMES.riskScan);
     try {
       await Promise.all(requiredTools.map((name) => this.waitForTool(name, {

package/lib/web.js

@@ -460,6 +460,7 @@ export function mountWebRoutes(wctx, { logger, report, TOOL_NAME, SKILL_NAME })
           const artifacts = await artifactStore.createBundle(taskId, {
             rows: payload.rows,
             headers: payload.headers,
+            fieldSelection: readyTask.fieldSelection,
             exceptionRows: payload.exceptionRows,
             baseName: payload.baseName || readyTask.title,
           });

package/lib/workflow-contract.js

@@ -117,6 +117,15 @@ export const FIELD_CATALOG = Object.freeze([
   }),
 ]);
 
+export const FIELD_LABELS = Object.freeze(Object.fromEntries(
+  FIELD_CATALOG.flatMap((group) => group.fields.map((field) => [field.id, field.label])),
+));
+
+export function fieldLabel(fieldId) {
+  const id = String(fieldId ?? '').trim();
+  return FIELD_LABELS[id] ?? id;
+}
+
 const FIELD_IDS = new Set(FIELD_CATALOG.flatMap((group) => group.fields.map((field) => field.id)));
 const STAGE_IDS = new Set(WORKFLOW_STAGES.map((stage) => stage.id));
 const STATE_IDS = new Set(WORKFLOW_STATES);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-data-cleaning-agent",
-  "version": "0.6.1",
+  "version": "0.6.2",
   "description": "Clean, complete, and profile enterprise name lists in DeepSeek Harness — a data cleaning & completion agent plugin with local CSV/XLSX/JSON engine and optional Qichacha (QCC) MCP enrichment. Maintained by Qichacha/QCC.",
   "type": "module",
   "main": "lib/index.js",
@@ -33,6 +33,7 @@
     "docs/RELEASE-0.5.3.md",
     "docs/RELEASE-0.6.0.md",
     "docs/RELEASE-0.6.1.md",
+    "docs/RELEASE-0.6.2.md",
     "docs/UI-WORKFLOW-V2.md",
     "docs/UI-WORKFLOW-V2-MIGRATION.md",
     "docs/UI-WORKFLOW-V2-ACCEPTANCE.md",