shlouai/dsh-debate
Stop asking your agent what it thinks. Make it hold a trial.
Project Overview项目介绍
dsh-debate is a DSH-native debate plugin for DeepSeek Harness, distributed as an npm bundle named @shlouai/dsh-debate and installed into a dsh profile without modifying the harness installation or its checkout. It exposes exactly three tools that split a formal argument across several model turns: debate_open fixes the motion and round count and returns a debate_id; debate_round spends precisely one round by spawning two fresh, isolated FOR and AGAINST subagents that never see the judging conversation or each other's personas; and debate_verdict is the main agent's single ruling pass, returning a round-by-round review and the winner as pro, con, or draw.
The typical workflow is asking a judgment-prone question such as "should we adopt framework X" or "is this contract clause safe to sign", watching two adversarial children research the workspace and the web, read each other's speeches, and rebut with citations, and finally receiving the judge's reasoning alongside the full transcript. The whole debate is projected into one folded Chat card in the DSH Web UI that fills in round by round, with built-in zh and en dictionaries, and the card survives a page reload because the plugin records its state inside the meta of ordinary tool/result events rather than declaring a custom session event type.
Dependencies are Node ^22.19 || >=24, strict TypeScript, and pnpm; the build runs against a deepseek-harness checkout, so contributors need that source tree locally. Debaters are restricted by tools.restrict() to a read-only allow list that includes read, glob, grep, web_search, and web_fetch, so they cannot write files or run commands; missing or unauthenticated tools degrade by being dropped once and logged. maxRounds defaults to 8 with two to three rounds recommended, the live debate is process-local and cannot be shared across sessions, and version 0.1.0 is explicitly experimental with the tool surface and config schema still subject to change.
dsh-debate 是 DeepSeek Harness(DSH)原生的辩论插件,以 bundle 形式安装到 dsh profile,不改动 Harness 安装目录。它通过三个工具把一场正式辩论拆给主 agent 调度:debate_open 锁定议题与回合数并返回 debate_id;debate_round 每调用一次跑一轮,派出互相隔离、互不可见的新建 FOR / AGAINST 子 agent,双方都默认挂载 read glob grep web_search web_fetch 用于取证;debate_verdict 由主 agent 在最后一轮给出逐回合评审与胜方结论。
典型场景是用户向 agent 提出"是否迁移到 X"这类容易自我合理化的判断题:插件启动后两条对立子线带着真实证据交锋,主 agent 直到辩论结束才打破沉默裁定,整段纪要作为一张折叠 Chat 卡片在 DSH Web UI 中随回合逐步展开。适合在决策分歧大、需先穷尽反对意见的架构选型、风险评估、对外承诺等场景使用,不适合需要多轮来回确认的事实问答。
依赖 Node ^22.19 || >=24、严格 TypeScript 与 pnpm,源码仍需绑定 deepseek-harness checkout 才能构建。debater 强制只读 tools.restrict(),无法写文件或执行命令;默认 maxRounds=8,两三轮为常用区间。版本 0.1.0 仍标 experimental,工具面与配置 schema 可能变动,npm 包名为 @shlouai/dsh-debate,许可证 MIT。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-debate(shlouai/dsh-debate)
仓库:https://github.com/shlouai/dsh-debate
本站详情页:https://www.yhbd.top/plugins/shlouai-dsh-debate/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-09-03 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 2 stars - very few users, little community feedback星标只有 2,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add @shlouai/dsh-debate
把 shlouai/dsh-debate 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-debate
Stop asking your agent what it thinks. Make it hold a trial.
A DeepSeek Harness plugin that answers a hard question by staging a formal debate — two adversarial subagents argue opposite sides with real research, and the main agent rules on the transcript.
English · 简体中文

Why
Ask an agent "should we migrate to X?" and you get one voice reasoning in one direction. It will find the arguments that support wherever it started, because nothing in the loop is paid to attack them.
dsh-debate puts an adversary in the loop. The FOR side and the AGAINST side are separate one-shot subagents that never see your conversation, never see the judge's opinion, and are each told to win. Both may read the workspace and search the web before speaking, so a claim is something a debater can show rather than something it remembers. Only after the last round does the main agent break its silence and rule.
What you get back is not a confident paragraph. It is a transcript where the strongest case against your idea was made on purpose, by something that wanted to beat it.
How it works
sequenceDiagram
autonumber
actor User
participant Judge as Judge<br/>your agent
participant For as FOR debater<br/>fresh child
participant Against as AGAINST debater<br/>fresh child
User->>Judge: Debate whether we should adopt X, 2 rounds
Judge->>Judge: debate_open — fix the motion and round count
loop each round — debate_round
Judge->>For: motion + full transcript so far
For->>For: read / glob / grep / web_search / web_fetch
For-->>Judge: speech FOR
Judge->>Against: motion + transcript, including the speech just made
Against->>Against: research and rebut
Against-->>Judge: speech AGAINST
end
Judge->>Judge: debate_verdict — assess round by round, rule once
Judge-->>User: winner, reasoning, and the whole transcript
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
Small-tailqwq/dsh-deep-whale
d-dev0101/open-sea-skin
kingOfSoySauce/dsh-liang-skin
RevolutionLA/dsh-dream-skin
Fishquito7/dsh-skill-mcp-panel
01Virex/dsh-status-rotator
ymh0000123/dsh-theme-endfield
SLin-code/dsh-custom-skin