dsh-data-cleaning-agent 0.8.12 → 0.8.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +5 -0
- package/README.en.md +1 -1
- package/README.md +1 -1
- package/lib/artifacts.js +2 -0
- package/lib/client.js +17 -5
- package/lib/qcc-command.js +1 -0
- package/lib/qcc-field-catalog.js +2 -0
- package/lib/qcc-runs.js +4 -1
- package/lib/qcc.js +20 -2
- package/package.json +2 -1
package/CHANGELOG.md
CHANGED
package/README.en.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
> 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.
|
|
4
4
|
>
|
|
5
|
-
> Current source version / 当前源码版本: **0.8.
|
|
5
|
+
> Current source version / 当前源码版本: **0.8.13** (stable release)
|
|
6
6
|
|
|
7
7
|
This release fixes misleading import errors after a successful upload. Files are parsed automatically, with persistent source, filename, and row-count status; text parsing handles only newly pasted content. The same file can be selected again, failed parsing preserves existing data, and pending pasted content must be parsed or cleared before continuing. Automatic mapping for 128 fields, blank-cell enrichment in original columns, QCC-blue menus, the resizable workbench, and native DSH sending remain unchanged. Existing download artifacts are not rewritten.
|
|
8
8
|
|
package/README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
> 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。
|
|
4
4
|
>
|
|
5
|
-
> 当前源码版本 / Current source version: **0.8.
|
|
5
|
+
> 当前源码版本 / Current source version: **0.8.13**(正式版本)
|
|
6
6
|
|
|
7
7
|
本版修复文件上传成功后的导入状态误报:文件选择后自动解析,当前来源、文件名和行数持续显示;文本解析仅处理新粘贴内容。支持重新选择同一文件,解析失败保留现有数据,新粘贴内容解析或清空后再进入下一步。保留 128 字段智能映射、原列补空、企查查蓝菜单、可调宽工作台及 DSH 原生发送机制。历史下载文件不自动改写。
|
|
8
8
|
|
package/lib/artifacts.js
CHANGED
|
@@ -21,6 +21,7 @@ const SYSTEM_FIELD_LABELS = Object.freeze({
|
|
|
21
21
|
biz_status: '经营状态',
|
|
22
22
|
risk_tags: '风险标签',
|
|
23
23
|
qcc_match_status: '匹配状态',
|
|
24
|
+
qcc_field_issues: '字段补全待核验原因',
|
|
24
25
|
qcc_source: '数据来源',
|
|
25
26
|
qcc_error: '错误原因',
|
|
26
27
|
match_status: '匹配状态',
|
|
@@ -115,6 +116,7 @@ function normalizeRows(value) {
|
|
|
115
116
|
}
|
|
116
117
|
|
|
117
118
|
function exceptionReason(row) {
|
|
119
|
+
if (row?.qcc_field_issues) return String(row.qcc_field_issues).slice(0, 2000);
|
|
118
120
|
const status = String(
|
|
119
121
|
row?.qcc_match_status
|
|
120
122
|
?? row?.match_status
|
package/lib/client.js
CHANGED
|
@@ -199,7 +199,7 @@ window.__ModuleLoader__.load({
|
|
|
199
199
|
const needle = String(query || '').trim().toLowerCase();
|
|
200
200
|
const [, label, fields, tool] = group;
|
|
201
201
|
if (!needle || `${label} ${tool || ''}`.toLowerCase().includes(needle)) return fields;
|
|
202
|
-
return fields.filter(([id, fieldLabel]) => `${id} ${fieldLabel}`.toLowerCase().includes(needle));
|
|
202
|
+
return fields.filter(([id, fieldLabel]) => `${id} ${fieldLabel} ${(MAPPING_ALIASES[id] || []).join(' ')}`.toLowerCase().includes(needle));
|
|
203
203
|
}
|
|
204
204
|
|
|
205
205
|
/** 客户端所需服务:与 mcp-connector 对齐(槽位 + 会话/工作区/输入机)。 */
|
|
@@ -1139,6 +1139,13 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
1139
1139
|
['equity_freeze', '股权冻结'],
|
|
1140
1140
|
];
|
|
1141
1141
|
const FIELD_GROUPS = [
|
|
1142
|
+
// Shared contract mirror: checked against qcc-field-contracts in tests.
|
|
1143
|
+
['actual_controller', '实际控制人', [
|
|
1144
|
+
['actual_controller_name', '实际控制人名称'],
|
|
1145
|
+
['actual_controller_direct_ratio', '实控人直接持股比例'],
|
|
1146
|
+
['actual_controller_total_ratio', '实控人总持股比例'],
|
|
1147
|
+
['actual_controller_voting_ratio', '实控人表决权比例'],
|
|
1148
|
+
], 'get_actual_controller'],
|
|
1142
1149
|
['company_registration', '企业工商信息', [
|
|
1143
1150
|
['company_name', '企业名称'], ['credit_no', '统一社会信用代码'], ['reg_no', '注册号'],
|
|
1144
1151
|
['org_no', '组织机构代码'], ['tax_no', '纳税人识别号'], ['reg_status', '登记状态'],
|
|
@@ -1203,6 +1210,7 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
1203
1210
|
['risk_tags', '风险标签'],
|
|
1204
1211
|
['qcc_match_status', '匹配状态'],
|
|
1205
1212
|
['qcc_source', '数据来源'],
|
|
1213
|
+
['qcc_field_issues', '字段补全待核验原因'],
|
|
1206
1214
|
['qcc_error', '错误原因'],
|
|
1207
1215
|
['match_status', '匹配状态'],
|
|
1208
1216
|
['input_company', '原始企业名称'],
|
|
@@ -1434,6 +1442,10 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
1434
1442
|
}
|
|
1435
1443
|
|
|
1436
1444
|
const MAPPING_ALIASES = {
|
|
1445
|
+
actual_controller_name: ['实控人', '实际控制人', '企业实控人名称', '企业实际控制人', '企业实控人名称(自然人请填写姓名)'],
|
|
1446
|
+
actual_controller_direct_ratio: ['实际控制人直接持股比例'],
|
|
1447
|
+
actual_controller_total_ratio: ['实际控制人总持股比例'],
|
|
1448
|
+
actual_controller_voting_ratio: ['实际控制人表决权比例'],
|
|
1437
1449
|
company_name: ['name', 'company', '公司名称', '单位名称', '企业全称', '公司全称', '主体标识'],
|
|
1438
1450
|
credit_no: ['creditCode', 'unified_credit_code', '信用代码', '社会信用代码', '统一信用代码', 'USCC'],
|
|
1439
1451
|
reg_no: ['registration_no', '工商注册号'],
|
|
@@ -3584,7 +3596,7 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
3584
3596
|
qccRunId: run.runId,
|
|
3585
3597
|
summary: {
|
|
3586
3598
|
total: Number(summary.totalRows ?? runtime.rows.length),
|
|
3587
|
-
exact: Number(summary.enriched ?? 0),
|
|
3599
|
+
exact: Number(summary.enriched ?? 0) + Number(summary.fieldReview ?? 0),
|
|
3588
3600
|
candidate: reviewRequired,
|
|
3589
3601
|
confirmed: 0,
|
|
3590
3602
|
unresolved: Number(summary.unresolved ?? summary.missingName ?? 0),
|
|
@@ -3605,7 +3617,7 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
3605
3617
|
completed: Number(summary.enriched ?? 0),
|
|
3606
3618
|
unchanged: Number(summary.unresolved ?? 0) + Number(summary.missingName ?? 0),
|
|
3607
3619
|
failed: Number(summary.failed ?? 0),
|
|
3608
|
-
reviewRequired: 0,
|
|
3620
|
+
reviewRequired: Number(summary.fieldReview ?? 0),
|
|
3609
3621
|
callsUsed: Array.isArray(run.audit) ? run.audit.length : 0,
|
|
3610
3622
|
},
|
|
3611
3623
|
});
|
|
@@ -3904,7 +3916,7 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
3904
3916
|
? qccRun.summary?.enriched ?? 0
|
|
3905
3917
|
: cachedTask?.enrichmentSummary?.completed;
|
|
3906
3918
|
const qccReviewCount = qccRun
|
|
3907
|
-
? qccRun.summary?.ambiguous ?? 0
|
|
3919
|
+
? (qccRun.summary?.ambiguous ?? 0) + (qccRun.summary?.fieldReview ?? 0)
|
|
3908
3920
|
: cachedTask?.enrichmentSummary?.reviewRequired
|
|
3909
3921
|
?? cachedTask?.matchSummary?.reviewRequired;
|
|
3910
3922
|
const stat = (label, value, tone) => h('div', { className: 'dcAgentCard' },
|
|
@@ -4100,7 +4112,7 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
4100
4112
|
h('h3', null, `任务 ${qccRun.runId} · ${qccRun.state}`),
|
|
4101
4113
|
h('div', { className: 'dcAgentGrid' },
|
|
4102
4114
|
stat('已补全', qccRun.summary?.enriched ?? 0, 'good'),
|
|
4103
|
-
stat('待核验', qccRun.summary?.ambiguous ?? 0
|
|
4115
|
+
stat('待核验', (qccRun.summary?.ambiguous ?? 0) + (qccRun.summary?.fieldReview ?? 0), (qccRun.summary?.ambiguous || qccRun.summary?.fieldReview) > 0 ? 'warn' : null),
|
|
4104
4116
|
stat('未匹配', qccRun.summary?.unresolved ?? 0, (qccRun.summary?.unresolved ?? 0) > 0 ? 'warn' : null),
|
|
4105
4117
|
stat('失败', qccRun.summary?.failed ?? 0, (qccRun.summary?.failed ?? 0) > 0 ? 'bad' : null),
|
|
4106
4118
|
),
|
package/lib/qcc-command.js
CHANGED
|
@@ -268,6 +268,7 @@ export function registerQccCommandTool(tools, commands) {
|
|
|
268
268
|
totalRows: { type: 'integer' },
|
|
269
269
|
uniqueCompanies: { type: 'integer' },
|
|
270
270
|
enriched: { type: 'integer' },
|
|
271
|
+
fieldReview: { type: 'integer' },
|
|
271
272
|
ambiguous: { type: 'integer' },
|
|
272
273
|
unresolved: { type: 'integer' },
|
|
273
274
|
failed: { type: 'integer' },
|
package/lib/qcc-field-catalog.js
CHANGED
|
@@ -5,6 +5,7 @@
|
|
|
5
5
|
* 任何明细列表(电话全集、海关资质、风险关联方等)都不得进入本目录。
|
|
6
6
|
*/
|
|
7
7
|
|
|
8
|
+
import { ACTUAL_CONTROLLER_GROUP } from 'qcc-field-contracts';
|
|
8
9
|
const field = (id, label, options = {}) => Object.freeze({ id, label, ...options });
|
|
9
10
|
const group = (id, label, sourceTool, fields, options = {}) => Object.freeze({
|
|
10
11
|
id,
|
|
@@ -173,6 +174,7 @@ export const QCC_FIELD_CATALOG = Object.freeze([
|
|
|
173
174
|
...RELATED_RISK_FACTORS.map(([id, label]) => field(`related_risk_${id}_count`, `关联风险-${label}条目数`)),
|
|
174
175
|
...RELATED_RISK_KEY_FACTORS.map(([id, label]) => field(`related_risk_${id}_party_count`, `关联风险-${label}命中关联方数`)),
|
|
175
176
|
], { releaseBatch: 'batch-2', catalogVersion: RISK_FACTOR_CATALOG_VERSION }),
|
|
177
|
+
ACTUAL_CONTROLLER_GROUP,
|
|
176
178
|
]);
|
|
177
179
|
|
|
178
180
|
export const QCC_FIELD_SOURCE_TOOL = Object.freeze(Object.fromEntries(
|
package/lib/qcc-runs.js
CHANGED
|
@@ -47,6 +47,7 @@ function deriveState(record) {
|
|
|
47
47
|
if (record.reviewQueue.length > 0) return 'awaiting-review';
|
|
48
48
|
if (record.errors.some((item) => item.error?.retryable)) return 'needs-retry';
|
|
49
49
|
if (record.errors.length > 0) return 'completed-with-errors';
|
|
50
|
+
if (record.rows.some(row => row.qcc_field_issues)) return 'completed-with-errors';
|
|
50
51
|
return 'completed';
|
|
51
52
|
}
|
|
52
53
|
|
|
@@ -55,7 +56,8 @@ function recomputeSummary(record) {
|
|
|
55
56
|
record.summary = {
|
|
56
57
|
...record.summary,
|
|
57
58
|
totalRows: record.rows.length,
|
|
58
|
-
enriched:
|
|
59
|
+
enriched: record.rows.filter(row => row.qcc_match_status === 'enriched' && !row.qcc_field_issues).length,
|
|
60
|
+
...(record.summary.fieldReview !== undefined || record.rows.some(row => row.qcc_field_issues) ? { fieldReview: record.rows.filter(row => row.qcc_field_issues).length } : {}),
|
|
59
61
|
ambiguous: count('ambiguous'),
|
|
60
62
|
unresolved: count('unresolved'),
|
|
61
63
|
failed: count('failed'),
|
|
@@ -231,6 +233,7 @@ export class G5RunStore {
|
|
|
231
233
|
...row,
|
|
232
234
|
...Object.fromEntries(Object.entries(result.fields || {}).filter(([key]) => row[key] == null || (typeof row[key] === 'string' && row[key].trim() === ''))),
|
|
233
235
|
qcc_match_status: 'enriched',
|
|
236
|
+
...(row.qcc_field_issues || result.fieldIssues ? { qcc_field_issues: Object.entries(result.fieldIssues || {}).map(([field, issue]) => field + ': ' + issue.message).join(';') } : {}),
|
|
234
237
|
qcc_source: 'qcc-mcp',
|
|
235
238
|
};
|
|
236
239
|
} else {
|
package/lib/qcc.js
CHANGED
|
@@ -8,6 +8,7 @@
|
|
|
8
8
|
* - 批量补全只在 Host/Web 内处理明细;模型仍只接收摘要。
|
|
9
9
|
*/
|
|
10
10
|
import { safeAuditEvent } from './qcc-safety.js';
|
|
11
|
+
import { projectActualController } from 'qcc-field-contracts';
|
|
11
12
|
import {
|
|
12
13
|
QCC_PHASE2_COMPANY_TOOLS,
|
|
13
14
|
QCC_PHASE2_HISTORY_TOOLS,
|
|
@@ -32,6 +33,7 @@ export const QCC_TOOL_NAMES = Object.freeze({
|
|
|
32
33
|
entityLookup: 'mcp__qcc-company__get_company_by_query',
|
|
33
34
|
registration: 'mcp__qcc-company__get_company_registration_info',
|
|
34
35
|
profile: 'mcp__qcc-company__get_company_profile',
|
|
36
|
+
actualController: 'mcp__qcc-company__get_actual_controller',
|
|
35
37
|
contact: 'mcp__qcc-company__get_contact_info',
|
|
36
38
|
listing: 'mcp__qcc-company__get_listing_info',
|
|
37
39
|
taxInvoice: 'mcp__qcc-company__get_tax_invoice_info',
|
|
@@ -548,7 +550,15 @@ export function mapCompanyRelatedRiskScanFields(value) {
|
|
|
548
550
|
const LEGACY_ENRICHMENT_FIELDS = Object.freeze([
|
|
549
551
|
'credit_no', 'legal_rep', 'reg_capital', 'establish_date', 'reg_status',
|
|
550
552
|
]);
|
|
553
|
+
export function mapActualControllerFields(value, match) {
|
|
554
|
+
if (value?.企业名称 && match?.companyName && value.企业名称 !== match.companyName) {
|
|
555
|
+
throw new QccBridgeError('QCC_ENTITY_MISMATCH', '实控人返回企业与已确认主体不一致');
|
|
556
|
+
}
|
|
557
|
+
const result=projectActualController(value);
|
|
558
|
+
return result.values;
|
|
559
|
+
}
|
|
551
560
|
const SOURCE_TOOL_CONFIG = Object.freeze({
|
|
561
|
+
get_actual_controller: Object.freeze({ name: QCC_TOOL_NAMES.actualController, map: mapActualControllerFields }),
|
|
552
562
|
get_company_registration_info: Object.freeze({ name: QCC_TOOL_NAMES.registration, map: mapRegistrationFields }),
|
|
553
563
|
get_company_profile: Object.freeze({ name: QCC_TOOL_NAMES.profile, map: mapProfileFields }),
|
|
554
564
|
get_contact_info: Object.freeze({ name: QCC_TOOL_NAMES.contact, map: mapContactFields, args: { excludeInvalidPhone: false } }),
|
|
@@ -917,6 +927,7 @@ export class QccHostBridge {
|
|
|
917
927
|
const lockedKey = String(match?.creditNo || match?.companyName || '').trim();
|
|
918
928
|
const sourceTools = sourceToolsForFieldSelection(options.fieldSelection, options.includeRisk);
|
|
919
929
|
let mapped = {};
|
|
930
|
+
const fieldIssues = {};
|
|
920
931
|
let legacyRiskTags = '';
|
|
921
932
|
for (const sourceTool of sourceTools) {
|
|
922
933
|
const config = SOURCE_TOOL_CONFIG[sourceTool];
|
|
@@ -924,6 +935,10 @@ export class QccHostBridge {
|
|
|
924
935
|
const response = await this.call(config.name, { searchKey: lockedKey, ...(config.args ?? {}) }, options);
|
|
925
936
|
const fields = config.map(response.data, match);
|
|
926
937
|
mapped = mergeMappedFields(mapped, fields);
|
|
938
|
+
if (sourceTool === 'get_actual_controller') {
|
|
939
|
+
Object.assign(fieldIssues, Object.fromEntries(Object.entries(projectActualController(response.data).issues)
|
|
940
|
+
.filter(([field]) => options.fieldSelection?.includes(field))));
|
|
941
|
+
}
|
|
927
942
|
if (sourceTool === 'get_company_risk_scan') legacyRiskTags = mapRiskTags(response.data);
|
|
928
943
|
if (config.inspect) {
|
|
929
944
|
const catalog = config.inspect(response.data);
|
|
@@ -942,7 +957,8 @@ export class QccHostBridge {
|
|
|
942
957
|
}
|
|
943
958
|
const fields = projectSelectedFields(mapped, options.fieldSelection);
|
|
944
959
|
if (options.includeRisk) fields.risk_tags = legacyRiskTags;
|
|
945
|
-
return { status: 'enriched', companyName: String(match?.companyName ?? ''), fields
|
|
960
|
+
return { status: 'enriched', companyName: String(match?.companyName ?? ''), fields,
|
|
961
|
+
...(Object.keys(fieldIssues).length ? { fieldIssues } : {}) };
|
|
946
962
|
}
|
|
947
963
|
|
|
948
964
|
async enrichLockedCompany(selection, options = {}) {
|
|
@@ -1030,6 +1046,7 @@ export class QccHostBridge {
|
|
|
1030
1046
|
...Object.fromEntries(Object.entries(result.fields || {}).filter(([key]) => row[key] == null || (typeof row[key] === 'string' && row[key].trim() === ''))),
|
|
1031
1047
|
qcc_match_status: 'enriched',
|
|
1032
1048
|
qcc_source: 'qcc-mcp',
|
|
1049
|
+
...(row.qcc_field_issues || result.fieldIssues ? { qcc_field_issues: Object.entries(result.fieldIssues || {}).map(([field, issue]) => field + ': ' + issue.message).join(';') } : {}),
|
|
1033
1050
|
};
|
|
1034
1051
|
}
|
|
1035
1052
|
return { ...row, qcc_match_status: result?.status ?? 'failed' };
|
|
@@ -1046,7 +1063,8 @@ export class QccHostBridge {
|
|
|
1046
1063
|
const summary = {
|
|
1047
1064
|
totalRows: rows.length,
|
|
1048
1065
|
uniqueCompanies: names.length,
|
|
1049
|
-
enriched: outputRows.filter((row) => row.qcc_match_status === 'enriched').length,
|
|
1066
|
+
enriched: outputRows.filter((row) => row.qcc_match_status === 'enriched' && !row.qcc_field_issues).length,
|
|
1067
|
+
...(outputRows.some(row => row.qcc_field_issues) ? { fieldReview: outputRows.filter(row => row.qcc_field_issues).length } : {}),
|
|
1050
1068
|
ambiguous: outputRows.filter((row) => row.qcc_match_status === 'ambiguous').length,
|
|
1051
1069
|
unresolved: outputRows.filter((row) => row.qcc_match_status === 'unresolved').length,
|
|
1052
1070
|
failed: outputRows.filter((row) => row.qcc_match_status === 'failed').length,
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-data-cleaning-agent",
|
|
3
|
-
"version": "0.8.
|
|
3
|
+
"version": "0.8.13",
|
|
4
4
|
"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.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "lib/index.js",
|
|
@@ -99,6 +99,7 @@
|
|
|
99
99
|
"node": ">=20"
|
|
100
100
|
},
|
|
101
101
|
"dependencies": {
|
|
102
|
+
"qcc-field-contracts": "0.1.0",
|
|
102
103
|
"xlsx": "^0.18.5"
|
|
103
104
|
},
|
|
104
105
|
"peerDependencies": {
|