deepseekplugins

DeepSeek Harness plugin

dsh-research-lab

DSH-native multi-runtime baseline, ablation, and reproducible evaluation control plane

Docs & Rendering
Jump to install

Source facts

Repository
Harzva/dsh-research-lab
Latest update
Aug 17, 2026
Category
Docs & Rendering
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/Harzva/dsh-research-lab
Plugin: dsh-research-lab
Author: Harzva

Check the source files

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

File explorer3 files
README.mdSource · read only

DSH Research Lab

dsh-research-lab 是独立的 DeepSeek Harness 研究插件：在 DSH Web 内管理多推理 Runtime、固定 Baseline、生成消融矩阵，并冻结可复现的实验 Manifest。

开发者检索关键词：dsh、dsh-plugin、deepseek-harness、dsh-research-lab、reasoning-runtime、agent-evaluation、ablation-study。

> M0 边界：当前是 Manifest-first 控制面。它不会调用模型、不会产生 API 费用，也不宣称 Plan-and-Execute、Tree of Thoughts 或 Reflexion 已经可运行。

已实现

  • 独立 DSH 插件包 @harness-flow/dsh-research-lab。
  • DSH 原生入口：Settings → Plugins → Research Lab。
  • Runtime Catalog：ReAct Default、Plan Guided、Code Orchestration，以及明确标记为设计态的 Plan-and-Execute、ToT、Reflexion。
  • 固定 DSH、Profile、Preset、模型、数据、预算、指标与种子的 Baseline 协议。
  • Runtime × repetitions 消融矩阵，最多 64 个 planned runs。
  • 规范化 JSON + SHA-256 的确定性 Manifest。
  • DSH Home 私有、原子、幂等存储；API 不返回绝对路径或凭据。
  • Windows/Linux CI、TypeScript 构建和单元测试。

本地开发

要求 Node.js 22+、pnpm 11，以及当前已验证的 DSH 0.1.0-rc.6。

pnpm install
pnpm check
pnpm run pack:plugin

把生成的 .tgz 安装到 DSH Web Profile：

dsh plugin --profile web add .\artifacts\harness-flow-dsh-research-lab-0.1.0-m0.tgz --save-exact --ignore-scripts
dsh --profile web

文档

  • [ROADMAP](./ROADMAP.md) — 唯一执行控制面
  • [M0 PRD](./docs/prd.md)
  • [架构](./docs/architecture.md)
  • [Experiment Schema](./schemas/research-experiment.schema.json)
  • [M0 本地证据](./evidence/m0-2026-08-17.json)

本项目是社区项目，不代表 DeepSeek 官方背书。

Back to searchOpen GitHub repository

More related plugins

View category