dsh-data-cleaning-agent 0.9.4 → 0.9.6

package/CHANGELOG.md

@@ -4,6 +4,16 @@
 
 ## [Unreleased]
 
+## [0.9.6] - 2026-09-11
+
+- 任务结果报告降为统计卡片后的次要下载链接，不再与客户主结果并列展示文件卡片或预览按钮；窄侧栏自动换行。
+
+## [0.9.5] - 2026-09-11
+
+- 主结果 XLSX 仅保留客户原列和选定补全字段；执行状态、来源及诊断信息改为独立任务结果报告，状态中文化。
+- 来源记录实际调用的企查查 MCP server / 工具；历史缺失来源明确标注，不推断补造。
+- 新任务只生成 XLSX，下载区按文件将预览与明确的下载按钮相邻展示，异常清单仅在有异常时提供。
+
 ## [0.9.4] - 2026-09-10
 
 - 文件预览采用 CSV 式单行表格，长文本不再撑高整行；独立双向滚动区域固定表头与序号列，下载保持完整原值。

package/README.en.md

@@ -10,7 +10,7 @@ Related agents: [数据清洗补全](https://github.com/duhu2000/dsh-data-cleani
 
 > 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: **0.9.4** (stable release)
+> Current source version / 当前源码版本: **0.9.6** (stable release)
 
 This release unifies spreadsheet previews, column mapping, and enrichment scope across the prompt wizard and workbench. Mapping statuses use color and text; mapped fields automatically enter the scope, with optional extra fields collapsed. Multiple confirmed output columns may share a non-identity field while preserving non-empty values. It fixes saved drafts resetting the scope to five defaults and detects stale Host versions. Preparing a draft does not query QCC; sending starts execution. Fully restart DSH after upgrading. Existing download artifacts are not rewritten.
 

package/README.md

@@ -9,7 +9,7 @@
 数据清洗补全智能体：面向 Excel/CSV/JSON 企业名单，提供数据清洗、表格清洗、清洗补全、去重、企业数据补全与字段补全，支持企查查 MCP 和结果导出。
 
 ```sh
-dsh plugin --profile web add dsh-data-cleaning-agent@0.9.4
+dsh plugin --profile web add dsh-data-cleaning-agent@0.9.6
 ```
 
 请先满足下文的 DSH、连接器及侧边栏依赖要求；安装后完整停止并重启对应 Profile。
@@ -27,7 +27,7 @@ dsh plugin --profile web add dsh-data-cleaning-agent@0.9.4
 
 > 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: **0.9.4**（正式版本）
+> 当前源码版本 / Current source version: **0.9.6**（正式版本）
 
 本版上传表格后展示完整清单及空白数量，用绿色、琥珀色、红色及文字区分已通过、待确认和未匹配映射。已映射字段自动纳入补全范围，额外字段默认折叠；多个原列可经确认使用同一非主体字段，分别补空并保留非空原值。修复 Host 草稿重置为默认五字段的问题，增加前后端版本错配提示。生成说明不查询，发送才执行；升级后需完整重启 DSH，历史下载文件不自动改写。
 
@@ -67,7 +67,7 @@ dsh plugin --profile web add dsh-data-cleaning-agent
 DSH 原生会话：首页标题、产品说明与工作流会替换通用探索页；输入框左上角提供提示词生成器，支持
 粘贴名单、解析 Excel/CSV/JSON 或附加图片并选择清洗动作、补全字段。上传清洗、质量体检、匹配核验、
 字段补全和任务历史五个入口位于输入框下方，右侧工作台承载“上传数据 → 规则确认 → 数据匹配 →
-清洗补全 → 下载数据”五步闭环。完成后可下载结果与异常清单的 CSV/XLSX 四类 Host 耐久制品。
+清洗补全 → 下载数据”五步闭环。完成后可预览、下载清洗补全结果 XLSX 和独立任务结果报告 XLSX；有异常时另提供异常清单 XLSX。执行状态和来源信息不会追加到客户主结果中。
 
 0.8.1 起，在数据清洗补全会话的原生输入框粘贴图片，或在「提示词生成」的图片页
 拖入/选择 PNG、JPEG、WebP，会显示可点击放大的原生缩略图。用户可继续完成匹配规则、清洗项与补全字段，

package/docs/USER-GUIDE.md

@@ -43,7 +43,7 @@ bash <(curl -fsSL https://raw.githubusercontent.com/duhu2000/dsh-data-cleaning-a
 2. **规则确认**：映射企业名称/统一社会信用代码/注册号，选择清洗目标与补全字段；
 3. **数据匹配**：运行质量体检与主体匹配，多候选由人工确认；
 4. **清洗补全**：执行本地确定性清洗；需要 QCC 时先零调用估算，再由当前用户确认使用自己的账号额度；
-5. **下载数据**：生成结果 CSV/XLSX 与异常清单 CSV/XLSX，后续可从任务历史恢复下载。
+5. **下载数据**：生成清洗补全结果 XLSX 和独立任务结果报告 XLSX；有异常时另提供异常清单 XLSX。主结果仅保留客户原列与选定补全字段，报告记录中文执行状态、实际 MCP server / 工具及诊断信息。每个文件的预览与下载按钮相邻，后续可从任务历史恢复下载。
 
 0.8.11 起的原列回填规则：规则确认时同时检查「字段映射」和「输出字段」。已选字段优先填入已映射原列的空白单元格，非空原值保持不变，原表没有对应映射的已选字段才新增列。地址、网址、开业时间等推荐需确认含义；重复列需明确选定一列。未返回的数据不编造。结果预览、XLSX/CSV 及异常清单遵循同一规则；历史已生成文件不会自动改写。
 

package/lib/artifacts.js

@@ -31,6 +31,18 @@ const SYSTEM_FIELD_LABELS = Object.freeze({
   _exception_reason: '异常原因',
 });
 
+const isExecutionField = key => ['qcc_match_status', 'qcc_field_issues', 'qcc_field_notes', 'qcc_source', 'qcc_snapshot_note', 'qcc_error', 'match_status', '_exception_reason', 'error', '_incomplete'].includes(key);
+const STATUS_LABELS = { enriched: '已匹配并补全', exact: '精确匹配', candidate: '候选主体待确认', ambiguous: '多候选待确认',
+  review_required: '待核验', unresolved: '未匹配', not_found: '未找到', failed: '失败', error: '失败', partial: '部分完成', 'missing-name': '缺少主体名称' };
+function reportRow(row) {
+  const next = { ...row };
+  for (const key of ['qcc_match_status', 'match_status']) {
+    if (key in next) next[key] = STATUS_LABELS[next[key]] || (next[key] ? '待核验（未知状态）' : '未记录');
+  }
+  if (next.qcc_source === 'qcc-mcp') next.qcc_source = '企查查 MCP（历史记录未保存具体 server / 工具）';
+  return next;
+}
+
 export class ArtifactError extends Error {
   constructor(code, message, status = 400) {
     super(message);
@@ -228,20 +240,22 @@ export class WorkflowArtifactStore {
       mappings: input.mappings || [], fieldSelection: normalizeFieldSelection(input.fieldSelection),
     });
     const rows = projected.rows;
-    const headers = normalizeHeaders(projected.headers, rows);
+    const allowed = new Set([...(input.headers || []), ...normalizeFieldSelection(input.fieldSelection)]);
+    const headers = normalizeHeaders(projected.headers, rows).filter(key => !isExecutionField(key)
+      && (!allowed.size || allowed.has(key)));
     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)
       : projectCompletionResult({ rows: normalizeRows(input.exceptionRows), headers: input.headers || [],
         mappings: input.mappings || [], fieldSelection: normalizeFieldSelection(input.fieldSelection) }).rows;
-    const exceptionHeaders = normalizeHeaders([...headers, '_exception_reason'], exceptions);
+    const reportHeaders = normalizeHeaders([...headers, 'qcc_match_status', 'qcc_source'], rows).filter(key => headers.includes(key) || isExecutionField(key));
+    const exceptionHeaders = normalizeHeaders([...reportHeaders, '_exception_reason'], exceptions).filter(key => reportHeaders.includes(key) || isExecutionField(key));
     const baseName = safeFilePart(input.baseName, '数据清洗补全结果');
     const timestamp = this.nowFn();
     const definitions = [
-      { kind: 'complete', format: 'csv', fileName: `${baseName}.csv`, rows, headers, sheet: '清洗补全结果' },
       { kind: 'complete', format: 'xlsx', fileName: `${baseName}.xlsx`, rows, headers, sheet: '清洗补全结果' },
-      { kind: 'review', format: 'csv', fileName: `${baseName}-异常清单.csv`, rows: exceptions, headers: exceptionHeaders, sheet: '异常清单' },
-      { kind: 'review', format: 'xlsx', fileName: `${baseName}-异常清单.xlsx`, rows: exceptions, headers: exceptionHeaders, sheet: '异常清单' },
+      { kind: 'report', format: 'xlsx', fileName: `${baseName}-任务结果报告.xlsx`, rows: rows.map(reportRow), headers: reportHeaders, sheet: '任务结果报告' },
+      ...(exceptions.length ? [{ kind: 'review', format: 'xlsx', fileName: `${baseName}-异常清单.xlsx`, rows: exceptions.map(reportRow), headers: exceptionHeaders, sheet: '异常清单' }] : []),
     ];
     const artifacts = [];
     for (const definition of definitions) {

package/lib/client.js

@@ -762,6 +762,14 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
     .dcAgentArtifactList { display: flex; flex-wrap: wrap; gap: 10px; margin-top: 16px; min-width: 0; }
     .dcAgentArtifactList > .dcAgentButton { display: inline-flex; align-items: center; box-sizing: border-box; max-width: 100%; min-width: 0; height: auto; white-space: normal; overflow-wrap: anywhere; line-height: 1.5; text-decoration: none; }
     .dcAgentArtifactList > a.dcAgentButton { flex-basis: 100%; }
+    .dcAgentResultSummary { display: flex; flex-wrap: wrap; align-items: flex-end; gap: 12px; min-width: 0; }
+    .dcAgentResultSummary > .dcAgentGrid { flex: 1 1 500px; min-width: 0; }
+    .dcAgentReportLink { color: var(--dc-muted); font-size: 13px; text-decoration: underline; padding: 8px 0; }
+    .dcAgentReportLink:hover { color: var(--dc-action); }
+    .dcAgentReportLink[aria-disabled="true"] { opacity: .5; cursor: wait; }
+    .dcAgentArtifactList > .dcAgentCard { width: 100%; min-width: 0; box-sizing: border-box; }
+    .dcAgentArtifactList .dcAgentCard p { overflow-wrap: anywhere; margin: 0 0 10px; }
+    .dcAgentArtifactList .dcAgentCard .dcAgentButton { max-width: 100%; height: auto; white-space: normal; overflow-wrap: anywhere; }
     .dcAgentPreviewTable { min-width: 0; max-width: 100%; scrollbar-gutter: stable; }
 .dcAgentPreviewTable > .dcAgentTable {
   width: max-content; min-width: 100%; max-width: none;
@@ -4087,37 +4095,43 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
           h('div', { className: 'dcAgentRow' }, h('button', { type: 'button', className: 'dcAgentButton is-primary', onClick: () => actions.setStep('download') }, '进入下载数据')),
         );
       } else if (step === 'download') {
-        const availableArtifacts = (cachedTask?.artifacts || []).filter(artifact => artifact.kind !== 'review' || artifact.rowCount > 0);
+        const availableArtifacts = (cachedTask?.artifacts || []).filter(artifact => artifact.format === 'xlsx' && (artifact.kind !== 'review' || artifact.rowCount > 0));
+        const resultArtifacts = availableArtifacts.filter(artifact => artifact.kind !== 'report');
+        const reportArtifact = availableArtifacts.find(artifact => artifact.kind === 'report');
         const canCreateArtifacts = Boolean(exportRows()?.length) && ['rules_confirmed', 'diagnosed', 'export_ready', 'partial'].includes(cachedTask?.state);
         pane = h('div', { className: 'dcAgentPane' },
           h('p', { className: 'dcAgentHint' }, '结果文件由 Host 保存；有失败、未匹配或待核验记录时展示异常清单。任务或插件重启后，可从任务历史继续下载；无需再次调用企查查。'),
-          h('div', { className: 'dcAgentGrid' },
+          h('div', { className: 'dcAgentResultSummary' }, h('div', { className: 'dcAgentGrid' },
             stat('输入行数', dataset ? dataset.rowCount : workflowTask?.source?.rowCount ?? '—'),
             stat('匹配补全', qccEnrichedCount, qccEnrichedCount > 0 ? 'good' : null),
             stat('待核验', qccReviewCount, qccReviewCount > 0 ? 'warn' : null),
             stat('任务状态', WORKFLOW_STATE_LABELS[cachedTask?.state] || cachedTask?.state || '进行中'),
             stat('失败', qccFailedCount, qccFailedCount > 0 ? 'bad' : null),
-          ),
-          availableArtifacts.length ? h('div', { className: 'dcAgentArtifactList' },
-            availableArtifacts.filter(artifact => artifact.format === 'xlsx').map(artifact => h('a', {
+          ), reportArtifact ? h('a', {
+            className: 'dcAgentReportLink',
+            href: `/data-cleaning/api/workflow/tasks/${encodeURIComponent(cachedTask.id)}/artifacts/${encodeURIComponent(reportArtifact.id)}`,
+            download: reportArtifact.fileName, 'aria-disabled': busy ? 'true' : undefined,
+            onClick: event => { event.preventDefault(); if (!busy) downloadArtifact(reportArtifact); },
+          }, '下载任务结果报告') : null),
+          resultArtifacts.length ? h('div', { className: 'dcAgentArtifactList' },
+            resultArtifacts.map(artifact => h('div', { key: artifact.id, className: 'dcAgentCard' },
+              h('p', { className: 'dcAgentHint' }, artifact.fileName),
+              h('div', { className: 'dcAgentRow' }, h('a', {
               key: 'preview-' + artifact.id, className: 'dcAgentButton',
               href: `/data-cleaning/api/workflow/tasks/${encodeURIComponent(cachedTask.id)}/artifacts/${encodeURIComponent(artifact.id)}?preview=1`,
               target: '_blank', rel: 'noopener noreferrer',
-            }, `预览 / 打开：${artifact.fileName}`)),
-            availableArtifacts.map((artifact) => h('button', {
+            }, '预览 / 打开'), h('button', {
               key: artifact.id,
               type: 'button',
               className: `dcAgentButton${artifact.kind === 'complete' && artifact.format === 'xlsx' ? ' is-primary' : ''}`,
               disabled: busy,
               onClick: () => downloadArtifact(artifact),
               'aria-label': `下载 ${artifact.fileName}`,
-            }, `${artifact.kind === 'review' ? '异常清单' : '清洗补全结果'} ${String(artifact.format).toUpperCase()} · ${artifact.rowCount} 行`)),
+            }, `下载${artifact.kind === 'review' ? '异常清单' : '清洗补全结果'} XLSX · ${artifact.rowCount} 行`)))),
           ) : h('div', null,
             h('div', { className: 'dcAgentRow' },
               h('button', { type: 'button', className: 'dcAgentButton is-primary', disabled: busy || !canCreateArtifacts, onClick: () => createAndDownload('complete', 'xlsx') }, '生成并下载结果 XLSX'),
-              h('button', { type: 'button', className: 'dcAgentButton', disabled: busy || !canCreateArtifacts, onClick: () => createAndDownload('complete', 'csv') }, '生成并下载结果 CSV'),
               qccReviewCount > 0 ? h('button', { type: 'button', className: 'dcAgentButton', disabled: busy || !canCreateArtifacts, onClick: () => createAndDownload('review', 'xlsx') }, '生成并下载异常清单 XLSX') : null,
-              qccReviewCount > 0 ? h('button', { type: 'button', className: 'dcAgentButton', disabled: busy || !canCreateArtifacts, onClick: () => createAndDownload('review', 'csv') }, '生成并下载异常清单 CSV') : null,
             ),
             !canCreateArtifacts ? h('p', { className: 'dcAgentHint' }, '请先完成规则确认与清洗补全；历史任务若尚未生成制品，需要重新上传源文件。') : null,
           ),

package/lib/qcc.js

@@ -921,7 +921,7 @@ export class QccHostBridge {
     );
     const match = classifyEntityMatch(lookup.data);
     if (match.status !== 'exact') return match;
-    return this.enrichMatchedCompany(match, options);
+    return this.enrichMatchedCompany(match, { ...options, lookupTool: lookup.toolName });
   }
 
   async enrichMatchedCompany(match, options = {}) {
@@ -930,11 +930,13 @@ export class QccHostBridge {
     let mapped = {};
     const fieldIssues = {};
     const snapshotNotes = [];
+    const actualTools = options.lookupTool ? [options.lookupTool] : [];
     let legacyRiskTags = '';
     for (const sourceTool of sourceTools) {
       const config = SOURCE_TOOL_CONFIG[sourceTool];
       if (!config) continue;
       const response = await this.call(config.name, { searchKey: lockedKey, ...(config.args ?? {}) }, options);
+      actualTools.push(response.toolName);
       const fields = config.map(response.data, match);
       mapped = mergeMappedFields(mapped, fields);
       if (['get_beneficial_owners', 'get_financial_data'].includes(sourceTool)) {
@@ -965,6 +967,10 @@ export class QccHostBridge {
     const fields = projectSelectedFields(mapped, options.fieldSelection);
     if (options.includeRisk) fields.risk_tags = legacyRiskTags;
     return { status: 'enriched', companyName: String(match?.companyName ?? ''), fields,
+      source: [...new Set(actualTools)].map(name => {
+        const parts = /^mcp__(.+?)__(.+)$/.exec(name || '');
+        return parts ? `企查查 MCP · server: ${parts[1]} · 工具: ${parts[2]}` : `企查查 MCP · 工具: ${name || '未记录'}`;
+      }).join('；'),
       ...(snapshotNotes.length ? { snapshotNote: snapshotNotes.join('；') } : {}),
       ...(Object.keys(fieldIssues).length ? { fieldIssues } : {}) };
   }
@@ -1068,7 +1074,7 @@ export class QccHostBridge {
           ...row,
           ...Object.fromEntries(Object.entries(result.fields || {}).filter(([key]) => row[key] == null || (typeof row[key] === 'string' && row[key].trim() === ''))),
           qcc_match_status: 'enriched',
-          qcc_source: 'qcc-mcp',
+          qcc_source: result.source || '企查查 MCP（未记录具体 server / 工具）',
           ...(result.snapshotNote ? { qcc_snapshot_note: result.snapshotNote } : {}),
           ...(row.qcc_field_issues || result.fieldIssues ? { qcc_field_issues: Object.entries(result.fieldIssues || {}).filter(([, issue]) => issue.reviewRequired !== false).map(([field, issue]) => field + ': ' + issue.message).join('；') } : {}),
           ...(result.fieldIssues ? { qcc_field_notes: Object.entries(result.fieldIssues).filter(([, issue]) => issue.reviewRequired === false).map(([field, issue]) => field + ': ' + issue.message).join('；') } : {}),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-data-cleaning-agent",
-  "version": "0.9.4",
+  "version": "0.9.6",
   "description": "Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.",
   "type": "module",
   "main": "lib/index.js",