GPT Permission Strip · 0.1.1

Removes redundant sandbox permission arguments from GPT-family tool calls.

安装

Enable the plugin to process GPT-family tool calls automatically. Real escalation requests remain subject to the host.

平台归档 · 市场版本 0.1.1

45.0 KiB · zip。下载后核对摘要、来源及权限。代码在用户客户端安装后运行。

兼容性与平台: Node.js 22 or later and DSH tools service required. Scoped registration regression tested; complete escalation behavior in the live host has not been independently verified. · Windows、macOS、Linux
支持的 DSH 核心版本: 未声明 · 运行兼容性未验证；版本声明不代表实测通过。

dsh-gpt-perm-strip

A DeepSeek Harness plugin that runs only for GPT-family models. Before a tool body hits DSH's sandbox escalation check, it removes sandbox_permissions / justification that are not strictly wider than the current session.

Why

DSH requires sandbox_permissions to be strictly wider than the session. The same (or a narrower) mode fails immediately:

sandbox escalation to "danger-full-access" is not strictly wider than this call's current "danger-full-access" mode

GPT-family models habitually send a permission field even when the session already has that access. This plugin drops those leftover fields and leaves real escalations (workspace-write → danger-full-access) untouched.

tools/pre-execute cannot rewrite frozen arguments. The plugin wraps each tool's execute and passes a cloned argument object with the unnecessary fields removed. The durable tool/call record still shows what the model emitted.

GPT-only

Matching is by model id, not provider (OpenAI-compatible gateways often host GPT, Grok, and DeepSeek under one provider):

gpt-4o, gpt-5.6-sol, chatgpt-4o-latest, openai/gpt-4.1, ft:gpt-4o:…
optional: o1 / o3 / o4 (includeOpenAiReasoning, default on)

Grok and DeepSeek are ignored unless you add extraModelPatterns.

Repo: [repository withheld]

This marketplace build is distributed as a platform archive. The public GitHub repository may not contain this build's changes.

Config

Field	Default	Meaning
`includeOpenAiReasoning`	`true`	Treat o1/o3/o4 as GPT-family
`extraModelPatterns`	`[]`	Extra regexes against `provider`, `model`, or `provider/model`
`injectPrompt`	`true`	GPT-only runtime-context reminder
`logStrips`	`true`	Log each strip as `[gpt-perm-strip] stripped …`

Behavior

Session	GPT argument	Result
`danger-full-access`	`sandbox_permissions: danger-full-access`	stripped, call runs
`workspace-write`	`sandbox_permissions: workspace-write`	stripped
`workspace-write`	`sandbox_permissions: danger-full-access`	kept (real escalation)
`read-only`	`sandbox_permissions: workspace-write`	kept
non-GPT model	any permission	unchanged

permission / permissions are treated as sandbox fields only when the value is a known sandbox mode.

来源、权限与发布信息

dsh · 平台归档 · MIT · 公开免费下载

源码与许可

MIT；原包保留许可文件

SHA-256

d4347aa657cb2e426cb9e0dedc47d933df762d5e14e59db37f49e4cfdeb061d2

权限声明

Wrap tool execution and inspect requested sandbox permissions
Read session model and sandbox policy
Optionally add a session prompt and log removed fields

变更说明

Fix wrapping of scoped tool registrations.

发布时间

2026-10-31 15:18+08:00

已发布版本

0.1.2-nanoai.1 · MIT · 公开免费下载
0.1.1 · MIT · 公开免费下载
0.1.0 · MIT · 公开免费下载