kaiwangleo/xiwen--plugins-dsh-xiwen ↗★ 0
@kaiwangleo/dsh-xiwen
由 Xiwen 服务提供支持的 DeepSeek Harness 语义层分析工具插件。
AI 分析
核心用途是为 DSH 提供语义层分析能力。适合需要利用 Xiwen 服务对 Harness 运行过程进行语义化分析和监控的用户。必要条件是需配置并运行 Xiwen 后端服务。
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kaiwangleo/xiwen#a310ef1e97243c75ab167dd950aac206f7f33cbf&path:plugins/dsh-xiwen说明文档
阅读完整 README ↗Configuration
The bundled patch defaults to the loopback Xiwen service. To override it, add an xiwen row to the profile's cordis.patch.yml:
- id: xiwen
config:
baseUrl: 'http://127.0.0.1:8000'
apiToken: 'REPLACE_WITH_THE_BACKEND_API_AUTH_TOKEN'
timeoutMs: 120000
maxRows: 200
maxResultChars: 50000
includeProgressSummary: false
Do not commit a real apiToken. Omit it when the local backend has no token configured.
| Setting | Default | Meaning |
|---|---|---|
baseUrl | http://127.0.0.1:8000 | Xiwen service root. Only HTTP and HTTPS URLs without embedded credentials, query strings, or fragments are accepted. |
apiToken | unset | Optional Bearer token matching api.auth_token in the backend configuration. |
timeoutMs | 120000 | Whole-request timeout, including SSE consumption. |
maxRows | 200 | Maximum rows returned to the model; accepted range is 1–10,000. |
maxResultChars | 50000 | Maximum serialized row characters returned to the model; accepted range is 1,000–1,000,000. |
includeProgressSummary | false | When enabled, include the final state of observed progress steps in message for result events. |
Invalid configuration fails when the plugin loads. A trailing slash in baseUrl is accepted; the adapter appends /api/query exactly once.