DeepSeek Harness plugin

dsh-model-plus

DSH Web 插件:本地按供应商编辑模型思考强度/视觉/上下文;一键同步默认从 models.dev 补全。

Jump to install

Source facts

Repository
kingsunb/dsh-model-plus
Latest update
Aug 16, 2026
Category
Memory
GitHub stars
0
Format
plugin
Package path
dsh-model-plus
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
dsh-model-plus/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/kingsunb/dsh-model-plus/tree/HEAD/dsh-model-plus
Plugin: dsh-model-plus
Author: kingsunb

Check the source files

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

File explorer4 files
README.mdSource · read only
README language

@kingsunb/dsh-model-plus

中文文档

DSH Web plugin: on the Settings page, under "模型 Plus" (Models Plus), edit each model's reasoning-effort tiers, vision capability, context window, and default output limit per provider, entirely in your local configuration. One-click sync fills in missing fields from models.dev by model id.

Features

  • Per-provider, per-model configuration

- Reasoning-effort tiers (off / minimal / low / medium / high / xhigh / max) - Vision capability (input: text / image) - Context window contextWindow (tokens) - Default output limit maxTokens

  • Quick presets: apply common combinations in one click (reasoning off / basic 3-tier / all-open / vision + all-open)
  • models.dev sync: fill in reasoning tiers, context, maxTokens, vision by model id (only fills missing by default; can overwrite)
  • Add providers: URL + API key import, fetch model lists, auto-fetch on creation
  • Model testing: single or batch tests, customizable default prompt, SVG preview
  • Multi-provider switching: manage multiple providers on one settings page

Installation

dsh plugin --profile web add @kingsunb/dsh-model-plus

Restart dsh web, then open Settings → 模型 Plus.

Catalog sources

The sync settings page provides three choices:

  • Official models.dev: https://models.dev/api.json
  • China GitHub acceleration: https://gh-proxy.org/https://github.com/kingsunb/dsh-model-plus/raw/refs/heads/main/api.json
  • Custom address: any approved HTTPS catalog URL

The China source serves the api.json snapshot committed at this repository root through gh-proxy.org. The official models.dev source remains the default.

Architecture

  • Host half (lib/index.js): registers same-origin HTTP endpoints /api/plus/*

- bootstrap / list-models / save-model / apply-preset - add-provider / discover-models (models.dev enrichment when fetching models) - enrich-models (one-click sync / sync settings page: models.dev preview and apply) - test-model (model availability and creative output testing)

  • Client half (lib/client.js): registers the "模型 Plus" settings section

License

MIT