DeepSeek Harness plugin

dsh-local-diagnostics

Privacy-first in-memory diagnostics for DeepSeek Harness

Jump to install

Source facts

Repository
fengyufengzi/dsh-local-diagnostics
Latest update
Aug 19, 2026
Category
Memory
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/fengyufengzi/dsh-local-diagnostics
Plugin: dsh-local-diagnostics
Author: fengyufengzi

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer3 files
README.mdSource · read only

dsh-local-diagnostics

![CI](https://github.com/fengyufengzi/dsh-local-diagnostics/actions/workflows/ci.yml)

一个面向 DeepSeek Harness 的隐私优先、本地内存诊断插件。

它通过 Harness 已公开的 Cordis 扩展点观察运行状态,不修改 Agent Loop:

  • tools/execute:测量 dispatch 阶段耗时,并始终调用 next()
  • tools/result:统计最终成功、失败以及结构化错误码;
  • session/event:只统计事件类型;
  • agent/error:只统计错误类名;
  • diagnostics_report:返回当前 Session 的脱敏聚合报告。

隐私保证

插件不采集提示词、消息、工具参数、工具输出、错误消息、Session ID、文件路径或凭证,也不写磁盘、不发送网络请求。完整边界见 [docs/privacy.md](docs/privacy.md)。

环境要求

  • Node.js ^22.19.0 || >=24.0.0
  • pnpm 11.7.0
  • DeepSeek Harness 0.1.0-rc.6 系列

Harness 尚处于开发者预览阶段,插件 API 可能发生破坏性变化。

本地开发

corepack pnpm install
corepack pnpm run check

check 依次执行类型检查、单元测试、构建,并把真实 .tgz 安装到隔离的临时消费项目中验证发布入口。只运行打包消费测试:

corepack pnpm run build
corepack pnpm run test:package

安装到 DSH profile

从本项目目录安装当前 checkout:

corepack pnpm run build
npx @deepseek-ai/dsh plugin --profile web add .
npx @deepseek-ai/dsh --profile web --dump-config
npx @deepseek-ai/dsh --profile web

然后要求 Agent 调用 diagnostics_report。移除插件:

npx @deepseek-ai/dsh plugin --profile web remove dsh-local-diagnostics

配置

- insert:
    - id: local-diagnostics
      name: dsh-local-diagnostics
      config:
        maxDistinctValues: 128

maxDistinctValues 是每类统计保留的精确名称上限,超出的名称归入 <other>

当前限制

  • 数据仅覆盖插件本次加载之后的进程生命周期。
  • 重启和插件热重载都会清空统计。
  • timing 是 dispatch 阶段耗时,不含审批和结果渲染。
  • 第一版没有 UI、文件导出、OpenTelemetry 或跨进程聚合。

License

MIT