deepseekplugins

DeepSeek Harness plugin

dsh-gpt-tool-compat

Non-destructive DSH compatibility layer: strips escalation arguments that are guaranteed to fail validation (empty justification, unpaired fields, non-strictly-wider sandbox_permissions) from any

Tools & Capabilities
Jump to install

Source facts

Repository
YoungUsing/dsh-gpt-tool-compat
Latest update
Aug 15, 2026
Category
Tools & Capabilities
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/YoungUsing/dsh-gpt-tool-compat
Plugin: dsh-gpt-tool-compat
Author: YoungUsing

Check the source files

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

File explorer3 files
README.mdSource · read only

dsh-gpt-tool-compat

非破坏性的 DSH 工具调用兼容层。某些模型调用方（如通过第三方提供方路由的 gpt-5.6-terra）会给每一个工具调用都附上提权参数，导致调用在参数校验阶段失败：

{ "command": "...", "justification": "", "sandbox_permissions": "workspace-write" }

本插件在 tools/pre-execute（分发前）拦截，只剥离必然校验失败的提权参数，把调用还原成模型本意要执行的普通调用。它不会：改动原本能成功的调用、绕过真实提权审批、或阻塞任何它无法处理的调用。监听器注册在进程级 root 作用域，覆盖所有会话的 pwsh/bash 及文件系统工具族调用。

安装

方式 A：作为 bundle（推荐）

1. 把本包装进 web profile 的 node_modules：

``powershell cd $env:USERPROFILE\.dsh\profiles\web npm install <本包路径，如 D:\Users\yq\Documents\code-and-repos\dsh-workspace\dsh-gpt-tool-compat> ``

2. 在 ~\.dsh\profiles\web\package.json 的 dsh.profile.bundles 数组里加入 "dsh-gpt-tool-compat"：

``jsonc "dsh": { "profile": { "bundles": [ "@deepseek-ai/dsh-base", "@deepseek-ai/dsh-web-app", "dsh-gpt-tool-compat" ] } } ``

3. 重启 dsh web 服务，刷新页面。

方式 B：直接插行

1. 同上安装包到 profile 的 node_modules。 2. 在 ~\.dsh\profiles\web\cordis.patch.yml 里插入：

``yaml - insert: - id: gpt-tool-compat name: 'dsh-gpt-tool-compat' ``

3. 重启 dsh web 服务。

验证

重启后随便开一个会话，用带空 justification 的工具调用测试（或观察之前失败的那些会话重试）——调用应正常执行，不再报 invalid justification / not strictly wider。

原理与安全边界

  • 剥离规则只作用于四种在任何沙箱模式下都必然被拒的情况：空/非字符串 justification、sandbox_permissions 与 justification 不成对、以及请求的模式不是当前有效模式严格更宽的提权（如 danger-full-access 下任何提权请求）。
  • 真正的更宽提权（如 read-only → workspace-write + 有效理由）原样放行，照常走真实用户审批。
  • 任何意外异常都会被捕获并放行原调用——本层永远不会让一个调用变得更糟。

License

MIT

Back to searchOpen GitHub repository

More related plugins

View category