NanoAI
中文 English Sign in / Register

GPT Permission Strip · 0.1.2-nanoai.1

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

Install

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

Platform archive · Marketplace version 0.1.2-nanoai.1

46.0 KiB · zip。Check the digest, source and permissions after download. Code runs in the user's client after installation.

Download 0.1.2-nanoai.1
Compatibility and platforms
Node.js 22 or later and DSH tools service required. Registration argument regression tested; DSH 0.2.2-rc.1 live host behavior is not independently verified. · Windows, macOS, Linux
Supported DSH core versions
not declared · Runtime compatibility is not verified; declared versions do not establish tested support.

dsh-gpt-perm-strip

NanoAI-maintained derivative of the platform's 0.1.1 archive. Obtain this build from NanoAI; the upstream repository may not contain its changes. DSH 0.2.2-rc.1 runtime behavior has not been independently verified.

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: https://github.com/FengLingYaaa/dsh-gpt-perm-strip

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.

Source, permissions and release information

dsh · Platform archive · MIT · free public download

Source and license
MIT；the original package keeps its license file
SHA-256
387986fecbf6481e7878d49efe0b20d762f5fc0eb3e6289674fd29b3cfdde9ef
Upstream version and local build
0.1.2-nanoai.1 · Build 1
Cumulative changes from upstream
Build 1: 0.1.2-nanoai.1 Cumulative differences relative to upstream 0.1.2-nanoai.1; current build delta: - NanoAI derivative from platform 0.1.1 forwards registration arguments; original platform patches and MIT license retained. Previous release 0.1.1: retain (valid).
Permission declarations
  • Wrap tool execution and inspect requested sandbox permissions
  • Read session model and sandbox policy
  • Optionally add a session prompt and log removed fields
Changelog
Preserve tool registration conditions and additional arguments.
Published at

Published versions