DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Scientific Computing — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
S

@kiwifruit/dsh-scientific-computing

Scientific Computing

NumPy/SciPy scientific computing tool — integrated as a DSH Cordis plugin, allowing models to initiate arbitrary NumPy/SciPy computations through the math_compute tool

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:kiwifruit13/dsh-scientific-computing#771bec7ee4289c43e7dc479e77bb578fa05592f5
READMECompatibilityVersions

Compatibility and provenance

Scientific Computing is published as @kiwifruit/dsh-scientific-computing and currently resolves to version 0.1.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
8/26/2026

Versions

0.1.1stable
8/26/2026
Latest
0.1.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
GPL-3.0
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
8/26/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

README

DSH-Scientific-Computing

NumPy / SciPy 数学计算工具,以 DSH(DeepSeek Harness)Cordis 插件形式集成到 AI Agent 的工具调用链。

模型可通过 math_compute 工具随时发起任意 NumPy / SciPy 运算,返回结构化 JSON 结果。


目录结构

DSH-Scientific-Computing/
├── src/
│   └── index.js              # DSH Cordis 插件(ESM,name/Config/apply)
├── scripts/
│   ├── math_compute_tool.py  # Python 计算引擎(stdin JSON → stdout JSON,安全重构版)
│   ├── run_tests.py          # 30 用例回归测试(含注入防御)
│   └── verify_plugin.py      # 五层验证脚本
├── docs/
│   ├── 集成指南.md            # 权威操作指导(唯一真相源)
│   └── 坑与经验沉淀.md         # 踩坑记录
├── cordis.patch.yml          # 发布版 bundle patch(npm 包名)
├── package.json              # npm 包清单
├── LICENSE                   # GPL-3.0
├── README.md                 # 本文档
└── AGENTS.md / CLAUDE.md     # 项目规范

安装

方式一:npm(推荐)

dsh plugin --profile web add @kiwifruit/dsh-scientific-computing

方式二:源码直装

dsh plugin --profile web add file:/你的路径/DSH-Scientific-Computing

前置条件

  • Python 3.8+,已安装 numpy 和 scipy
  • DSH(dsh CLI 可用)
  • Node.js ≥ 18
pip install numpy scipy

快速验证

1. Python 引擎独立测试

echo '{"operation":"sum","args":[[1,2],[3,4]],"module":"numpy"}' \
  | python scripts/math_compute_tool.py

# → {"success": true, "result": {"type": "array", "value": 10}}

2. 全量回归测试

python scripts/run_tests.py
# PASS: 30/30 all passed

覆盖数组聚合、线性代数(含 solve/lstsq)、FFT、优化(lambda)、布尔参数、keepdims、注入防御、非法类型。

3. 插件合规验证

python scripts/verify_plugin.py

支持的运算

类别操作module
数组聚合sum, mean, std, var, min, max, argmin, argmax, cumsum, prod, tracenumpy
线性代数inv, det, eig, eigvals, svd, qr, norm, pinv, solvenumpy.linalg
信号处理fft, ifft, rfft, irfft, fft2, ifft2, fftfreqnumpy.fft
矩阵乘法dot, matmulnumpy
优化minimize, linprog, least_squares, rootscipy.optimize
其他normscipy.linalg

Lambda 函数传参

优化类操作需要传 lambda,须用字符串形式:

{
  "operation": "minimize",
  "module": "scipy.optimize",
  "kwargs": {
    "fun": "lambda x: x[0]**2 + x[1]**2",
    "x0": [1, 0]
  }
}

配置

通过 cordis.patch.yml 或 config 参数配置:

字段默认值说明
pythonPath'python'Python 解释器路径(系统 PATH 或绝对路径)
enginePath自动解析Python 引擎脚本路径;缺省从插件 install 位置自动解析

覆盖 enginePath

如需使用自定义 Python 脚本:

- insert:
    - id: scientific-computing
      name: '@kiwifruit/dsh-scientific-computing'
      config:
        pythonPath: 'python'
        enginePath: 'C:/custom/maths/math_compute_tool.py'

输出格式

成功

{
  "success": true,
  "result": {
    "type": "array" | "scalar" | "result" | "other",
    "value": [...]
  }
}

失败

{
  "success": false,
  "error": "Import error: No module named 'numpy'"
}

通信协议

插件 (JS)                    Python 引擎
   │                          │
   │── JSON stdin ──────────→│  module, operation, args, kwargs
   │←── JSON stdout ─────────│  success, result
   │                          │

验证清单

#检查项命令
1插件已安装dsh plugin --profile web list
2模块形状合法node -e "import('./src/index.js').then(m=>console.log(m.name))"
3引擎直连正常echo '{"operation":"sum","args":[[1,2]]}' | python scripts/math_compute_tool.py
4完整测试通过python scripts/run_tests.py
5合规验证通过python scripts/verify_plugin.py

发布到 npm

npm publish --access public

最后更新:2026-08-26