dsh-data-cleaning-agent 0.6.3 → 0.7.0

package/lib/workflow-contract.js

@@ -7,6 +7,8 @@
  *  - 历史、人员、招投标三域不属于当前版本字段目录。
  */
 
+import { QCC_FIELD_CATALOG } from './qcc-field-catalog.js';
+
 export const WORKFLOW_SCHEMA_VERSION = 2;
 
 export const WORKFLOW_STAGES = Object.freeze([
@@ -49,84 +51,28 @@ export const MATCH_STATUSES = Object.freeze([
 
 export const MATCH_ANCHORS = Object.freeze(['company_name', 'credit_no', 'reg_no']);
 
-export const FIELD_CATALOG = Object.freeze([
-  Object.freeze({
-    id: 'identity',
-    label: '基础工商信息',
-    fields: Object.freeze([
-      Object.freeze({ id: 'company_name', label: '企业名称', inputAnchor: true, defaultSelected: true }),
-      Object.freeze({ id: 'credit_no', label: '统一社会信用代码', inputAnchor: true, defaultSelected: true }),
-      Object.freeze({ id: 'reg_no', label: '注册号', inputAnchor: true }),
-      Object.freeze({ id: 'org_no', label: '组织机构代码' }),
-      Object.freeze({ id: 'reg_status', label: '登记状态', defaultSelected: true }),
-      Object.freeze({ id: 'legal_rep', label: '法定代表人', defaultSelected: true }),
-      Object.freeze({ id: 'reg_capital', label: '注册资本', defaultSelected: true }),
-      Object.freeze({ id: 'paid_capital', label: '实缴资本' }),
-      Object.freeze({ id: 'establish_date', label: '成立日期', defaultSelected: true }),
-      Object.freeze({ id: 'company_type', label: '企业类型' }),
-      Object.freeze({ id: 'registration_authority', label: '登记机关' }),
-      Object.freeze({ id: 'former_name', label: '曾用名' }),
-      Object.freeze({ id: 'english_name', label: '英文名' }),
-    ]),
-  }),
-  Object.freeze({
-    id: 'contact',
-    label: '地址与联系方式',
-    fields: Object.freeze([
-      Object.freeze({ id: 'registered_address', label: '注册地址', defaultSelected: true }),
-      Object.freeze({ id: 'province', label: '省份地区', matchAuxiliary: true }),
-      Object.freeze({ id: 'city', label: '城市', matchAuxiliary: true }),
-      Object.freeze({ id: 'district', label: '区县' }),
-      Object.freeze({ id: 'phone', label: '电话', matchAuxiliary: true }),
-      Object.freeze({ id: 'email', label: '邮箱' }),
-      Object.freeze({ id: 'website', label: '官网' }),
-    ]),
-  }),
-  Object.freeze({
-    id: 'operation',
-    label: '经营信息',
-    fields: Object.freeze([
-      Object.freeze({ id: 'business_scope', label: '经营范围' }),
-      Object.freeze({ id: 'industry_category', label: '国标行业' }),
-      Object.freeze({ id: 'industry_large', label: '一级行业' }),
-      Object.freeze({ id: 'industry_middle', label: '二级行业' }),
-      Object.freeze({ id: 'operating_period', label: '营业期限' }),
-      Object.freeze({ id: 'company_size', label: '企业规模' }),
-      Object.freeze({ id: 'company_profile', label: '企业简介' }),
-    ]),
-  }),
-  Object.freeze({
-    id: 'risk',
-    label: '风险摘要',
-    capability: 'qcc.risk',
-    fields: Object.freeze([
-      Object.freeze({ id: 'risk_summary', label: '风险摘要', capability: 'qcc.risk' }),
-      Object.freeze({ id: 'operating_exception', label: '经营异常摘要', capability: 'qcc.risk' }),
-      Object.freeze({ id: 'administrative_penalty', label: '行政处罚摘要', capability: 'qcc.risk' }),
-    ]),
-  }),
-  Object.freeze({
-    id: 'ipr',
-    label: '知识产权摘要',
-    capability: 'qcc.ipr',
-    fields: Object.freeze([
-      Object.freeze({ id: 'trademark_summary', label: '商标摘要', capability: 'qcc.ipr' }),
-      Object.freeze({ id: 'patent_summary', label: '专利摘要', capability: 'qcc.ipr' }),
-      Object.freeze({ id: 'software_copyright_summary', label: '软件著作权摘要', capability: 'qcc.ipr' }),
-    ]),
-  }),
-]);
+export const FIELD_CATALOG = QCC_FIELD_CATALOG;
 
 export const FIELD_LABELS = Object.freeze(Object.fromEntries(
   FIELD_CATALOG.flatMap((group) => group.fields.map((field) => [field.id, field.label])),
 ));
 
+// 输入清洗字段可以参与字段映射与本地质量检查，但不是当前 QCC 可补全字段，
+// 因此绝不能出现在 fieldSelection 或导出补全字段目录中。
+export const INPUT_ONLY_MAPPING_FIELDS = Object.freeze([
+  Object.freeze({ id: 'phone', label: '联系电话' }),
+]);
+
 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 ENRICHMENT_FIELD_IDS = new Set(FIELD_CATALOG.flatMap((group) => group.fields.map((field) => field.id)));
+const MAPPING_FIELD_IDS = new Set([
+  ...ENRICHMENT_FIELD_IDS,
+  ...INPUT_ONLY_MAPPING_FIELDS.map((field) => field.id),
+]);
 const STAGE_IDS = new Set(WORKFLOW_STAGES.map((stage) => stage.id));
 const STATE_IDS = new Set(WORKFLOW_STATES);
 
@@ -170,7 +116,7 @@ export function normalizeMappings(value) {
   return value.slice(0, 128).map((mapping) => ({
     sourceField: text(mapping?.sourceField),
     targetField: text(mapping?.targetField),
-  })).filter((mapping) => mapping.sourceField && FIELD_IDS.has(mapping.targetField));
+  })).filter((mapping) => mapping.sourceField && MAPPING_FIELD_IDS.has(mapping.targetField));
 }
 
 export function validateMappings(value) {
@@ -206,7 +152,7 @@ export function validateMappings(value) {
 }
 
 export function normalizeFieldSelection(value) {
-  return uniqueStrings(value).filter((field) => FIELD_IDS.has(field));
+  return uniqueStrings(value, 256).filter((field) => ENRICHMENT_FIELD_IDS.has(field));
 }
 
 export function normalizeWorkflowDraft(value = {}) {
@@ -248,6 +194,7 @@ export function publicWorkflowContract() {
     matchStatuses: MATCH_STATUSES,
     matchAnchors: MATCH_ANCHORS,
     fieldCatalog: FIELD_CATALOG,
+    inputOnlyMappingFields: INPUT_ONLY_MAPPING_FIELDS,
     crossCuttingCapabilities: [
       { id: 'prompt', label: '任务设置' },
       { id: 'profile', label: '质量体检' },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-data-cleaning-agent",
-  "version": "0.6.3",
+  "version": "0.7.0",
   "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",
@@ -35,6 +35,7 @@
     "docs/RELEASE-0.6.1.md",
     "docs/RELEASE-0.6.2.md",
     "docs/RELEASE-0.6.3.md",
+    "docs/RELEASE-0.7.0.md",
     "docs/UI-WORKFLOW-V2.md",
     "docs/UI-WORKFLOW-V2-MIGRATION.md",
     "docs/UI-WORKFLOW-V2-ACCEPTANCE.md",
@@ -43,7 +44,7 @@
   ],
   "scripts": {
     "test": "node --test",
-    "lint": "node --check lib/index.js && node --check lib/engine.js && node --check lib/artifacts.js && node --check lib/tools.js && node --check lib/skill.js && node --check lib/qcc-phase2.js && node --check lib/qcc-phase3.js && node --check lib/qcc-phase3-batch.js && node --check lib/qcc-phase2-acceptance.js && node --check lib/skill-enrich.js && node --check lib/jobs.js && node --check lib/workflow-contract.js && node --check lib/workflow.js && node --check lib/qcc-safety.js && node --check lib/qcc.js && node --check lib/qcc-command.js && node --check lib/qcc-runs.js && node --check lib/web.js && node --check lib/client.js && node --check scripts/check-readme-version.mjs && node --check scripts/check-market-registration.mjs && node --check scripts/g5-e2e.mjs && node --check scripts/phase3-e2e.mjs && node --check scripts/phase2-acceptance.mjs",
+    "lint": "node --check lib/index.js && node --check lib/engine.js && node --check lib/artifacts.js && node --check lib/tools.js && node --check lib/skill.js && node --check lib/qcc-field-catalog.js && node --check lib/qcc-phase2.js && node --check lib/qcc-phase3.js && node --check lib/qcc-phase3-batch.js && node --check lib/qcc-phase2-acceptance.js && node --check lib/skill-enrich.js && node --check lib/jobs.js && node --check lib/workflow-contract.js && node --check lib/workflow.js && node --check lib/qcc-safety.js && node --check lib/qcc.js && node --check lib/qcc-command.js && node --check lib/qcc-runs.js && node --check lib/web.js && node --check lib/client.js && node --check scripts/check-readme-version.mjs && node --check scripts/check-market-registration.mjs && node --check scripts/g5-e2e.mjs && node --check scripts/phase3-e2e.mjs && node --check scripts/phase2-acceptance.mjs",
     "docs:check": "node scripts/check-readme-version.mjs",
     "marketing:check": "node scripts/check-marketing.mjs",
     "verify-pack": "node scripts/verify-pack.mjs",