dsh-data-cleaning-agent 0.9.5 → 0.9.6
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 +4 -0
- package/README.en.md +1 -1
- package/README.md +2 -2
- package/lib/client.js +17 -5
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
package/README.en.md
CHANGED
|
@@ -10,7 +10,7 @@ Related agents: [数据清洗补全](https://github.com/duhu2000/dsh-data-cleani
|
|
|
10
10
|
|
|
11
11
|
> 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.
|
|
12
12
|
>
|
|
13
|
-
> Current source version / 当前源码版本: **0.9.
|
|
13
|
+
> Current source version / 当前源码版本: **0.9.6** (stable release)
|
|
14
14
|
|
|
15
15
|
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.
|
|
16
16
|
|
package/README.md
CHANGED
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
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。
|
|
10
10
|
|
|
11
11
|
```sh
|
|
12
|
-
dsh plugin --profile web add dsh-data-cleaning-agent@0.9.
|
|
12
|
+
dsh plugin --profile web add dsh-data-cleaning-agent@0.9.6
|
|
13
13
|
```
|
|
14
14
|
|
|
15
15
|
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@0.9.5
|
|
|
27
27
|
|
|
28
28
|
> 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。
|
|
29
29
|
>
|
|
30
|
-
> 当前源码版本 / Current source version: **0.9.
|
|
30
|
+
> 当前源码版本 / Current source version: **0.9.6**(正式版本)
|
|
31
31
|
|
|
32
32
|
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。
|
|
33
33
|
|
package/lib/client.js
CHANGED
|
@@ -762,6 +762,11 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
762
762
|
.dcAgentArtifactList { display: flex; flex-wrap: wrap; gap: 10px; margin-top: 16px; min-width: 0; }
|
|
763
763
|
.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; }
|
|
764
764
|
.dcAgentArtifactList > a.dcAgentButton { flex-basis: 100%; }
|
|
765
|
+
.dcAgentResultSummary { display: flex; flex-wrap: wrap; align-items: flex-end; gap: 12px; min-width: 0; }
|
|
766
|
+
.dcAgentResultSummary > .dcAgentGrid { flex: 1 1 500px; min-width: 0; }
|
|
767
|
+
.dcAgentReportLink { color: var(--dc-muted); font-size: 13px; text-decoration: underline; padding: 8px 0; }
|
|
768
|
+
.dcAgentReportLink:hover { color: var(--dc-action); }
|
|
769
|
+
.dcAgentReportLink[aria-disabled="true"] { opacity: .5; cursor: wait; }
|
|
765
770
|
.dcAgentArtifactList > .dcAgentCard { width: 100%; min-width: 0; box-sizing: border-box; }
|
|
766
771
|
.dcAgentArtifactList .dcAgentCard p { overflow-wrap: anywhere; margin: 0 0 10px; }
|
|
767
772
|
.dcAgentArtifactList .dcAgentCard .dcAgentButton { max-width: 100%; height: auto; white-space: normal; overflow-wrap: anywhere; }
|
|
@@ -4091,18 +4096,25 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
4091
4096
|
);
|
|
4092
4097
|
} else if (step === 'download') {
|
|
4093
4098
|
const availableArtifacts = (cachedTask?.artifacts || []).filter(artifact => artifact.format === 'xlsx' && (artifact.kind !== 'review' || artifact.rowCount > 0));
|
|
4099
|
+
const resultArtifacts = availableArtifacts.filter(artifact => artifact.kind !== 'report');
|
|
4100
|
+
const reportArtifact = availableArtifacts.find(artifact => artifact.kind === 'report');
|
|
4094
4101
|
const canCreateArtifacts = Boolean(exportRows()?.length) && ['rules_confirmed', 'diagnosed', 'export_ready', 'partial'].includes(cachedTask?.state);
|
|
4095
4102
|
pane = h('div', { className: 'dcAgentPane' },
|
|
4096
4103
|
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。'),
|
|
4097
|
-
h('div', { className: 'dcAgentGrid' },
|
|
4104
|
+
h('div', { className: 'dcAgentResultSummary' }, h('div', { className: 'dcAgentGrid' },
|
|
4098
4105
|
stat('输入行数', dataset ? dataset.rowCount : workflowTask?.source?.rowCount ?? '—'),
|
|
4099
4106
|
stat('匹配补全', qccEnrichedCount, qccEnrichedCount > 0 ? 'good' : null),
|
|
4100
4107
|
stat('待核验', qccReviewCount, qccReviewCount > 0 ? 'warn' : null),
|
|
4101
4108
|
stat('任务状态', WORKFLOW_STATE_LABELS[cachedTask?.state] || cachedTask?.state || '进行中'),
|
|
4102
4109
|
stat('失败', qccFailedCount, qccFailedCount > 0 ? 'bad' : null),
|
|
4103
|
-
),
|
|
4104
|
-
|
|
4105
|
-
|
|
4110
|
+
), reportArtifact ? h('a', {
|
|
4111
|
+
className: 'dcAgentReportLink',
|
|
4112
|
+
href: `/data-cleaning/api/workflow/tasks/${encodeURIComponent(cachedTask.id)}/artifacts/${encodeURIComponent(reportArtifact.id)}`,
|
|
4113
|
+
download: reportArtifact.fileName, 'aria-disabled': busy ? 'true' : undefined,
|
|
4114
|
+
onClick: event => { event.preventDefault(); if (!busy) downloadArtifact(reportArtifact); },
|
|
4115
|
+
}, '下载任务结果报告') : null),
|
|
4116
|
+
resultArtifacts.length ? h('div', { className: 'dcAgentArtifactList' },
|
|
4117
|
+
resultArtifacts.map(artifact => h('div', { key: artifact.id, className: 'dcAgentCard' },
|
|
4106
4118
|
h('p', { className: 'dcAgentHint' }, artifact.fileName),
|
|
4107
4119
|
h('div', { className: 'dcAgentRow' }, h('a', {
|
|
4108
4120
|
key: 'preview-' + artifact.id, className: 'dcAgentButton',
|
|
@@ -4115,7 +4127,7 @@ body:has(.dcAgentPromptBackdrop) { overflow: hidden; }
|
|
|
4115
4127
|
disabled: busy,
|
|
4116
4128
|
onClick: () => downloadArtifact(artifact),
|
|
4117
4129
|
'aria-label': `下载 ${artifact.fileName}`,
|
|
4118
|
-
}, `下载${artifact.kind === 'review' ? '异常清单' :
|
|
4130
|
+
}, `下载${artifact.kind === 'review' ? '异常清单' : '清洗补全结果'} XLSX · ${artifact.rowCount} 行`)))),
|
|
4119
4131
|
) : h('div', null,
|
|
4120
4132
|
h('div', { className: 'dcAgentRow' },
|
|
4121
4133
|
h('button', { type: 'button', className: 'dcAgentButton is-primary', disabled: busy || !canCreateArtifacts, onClick: () => createAndDownload('complete', 'xlsx') }, '生成并下载结果 XLSX'),
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-data-cleaning-agent",
|
|
3
|
-
"version": "0.9.
|
|
3
|
+
"version": "0.9.6",
|
|
4
4
|
"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.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "lib/index.js",
|