MIT-licensed DSH plugin (JavaScript) that gives text-only models multimodal reading via tool calling, then judges design fidelity — and steps aside automatically when DeepSeek ships native vision.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-06
License
MIT
01What can it help you accomplish?
Let a text-only model inside DeepSeek Harness read images and judge whether the implementation matches the mock
A design-fidelity verdict that traces back to evidence, plus a benchmark (4 fixtures, 23 injected defects, four pass lines) with every raw model transcript
Developers and design engineers running product design on DSH who need a text-only model to act as the referee in the fidelity loop
Borrow multimodal image-reading for any text-only model wired into DSH
The model calls `deepseek_vision` itself via tool calling; the image never enters the main model context and costs nothing unless the model decides to look
Users who bring their own OpenAI-compatible text endpoints into DSH and want those models to handle images
Step aside automatically once DeepSeek ships native vision
No changes needed: `deepseek_vision` self-rejects at runtime and the installer skips the core patch; the plugin can stay installed as-is
DSH users who care about plugin lifecycle and maintainability
02How to install into DeepSeek Harness
Prerequisites
- A DeepSeek Harness that can already hold a normal conversation — workspace selected and the main model key configured
- Node `^22.19 || >=24` (same as DSH)
- A BAILIAN_API_KEY from Alibaba Cloud Bailian (the plugin only handles the image-reading link)
Installation steps
- 01
Run `dsh plugin --profile web add dsh-design-qa`
$ dsh plugin --profile web add dsh-design-qa
- 02
cd into the installed folder: `${DSH_HOME:-$HOME/.dsh}/profiles/web/node_modules/dsh-design-qa`
- 03
Set the key: `export BAILIAN_API_KEY=<your key>`
- 04
Run `node install.mjs --route-only`
- 05
Run `node install.mjs --restart` (cold start; HMR is off)
Verify the integration
- Paste an image into the chat box and ask "what is this"
- Images go in by paste or drag — DSH's input has no separate upload button
Rollback
- Run `node install.mjs --revert-patches` to restore the patched DSH core files
- Then `dsh plugin --profile web remove dsh-design-qa`
03DSH integration and capability boundaries
Installed through the official dsh CLI (`dsh plugin add`); registers a `deepseek_vision` tool and patches the local DSH core so text-only models can read images.
deepseek_vision image-reading tool
image path / http(s) URL / attachment id→an answer to a question about the image
Image-paste core patch (3 DSH core edits)
running `node install.mjs --route-only`→text-only routes accept pasted images
Edits three files in the DSH core on disk (auto-backed-up; restorable via `node install.mjs --revert-patches`)Design-fidelity benchmark
mock and implementation images→a fidelity verdict plus 4 fixtures, 23 injected defects and four pass lines
04Who is it for? When not to use it?
Good for
- Developers and design engineers running product design on DSH who need a text-only model to act as the referee in the fidelity loop
- Users who bring their own OpenAI-compatible text endpoints into DSH and want those models to handle images
- DSH users who care about plugin lifecycle and maintainability
Not for
- The targeted model must support tool calling — otherwise it only sees a `[图片 …]` pointer and cannot call the tool. Confirm the endpoint accepts the `tools` parameter before wiring the route.
- Installation edits three DSH core files on disk. Uninstall must explicitly run `node install.mjs --revert-patches` first — otherwise the leftover patch tells the model to call a tool that no longer exists.
05Compatibility, maintenance and safety notes
- The targeted model must support tool calling — otherwise it only sees a `[图片 …]` pointer and cannot call the tool. Confirm the endpoint accepts the `tools` parameter before wiring the route.
- Installation edits three DSH core files on disk. Uninstall must explicitly run `node install.mjs --revert-patches` first — otherwise the leftover patch tells the model to call a tool that no longer exists.
- `deepseek_vision` reads one image at a time — multi-image comparison is not covered; side-by-side mock-vs-implementation needs to be assembled by the caller. Images behind login (Feishu, Notion) return 401/403 on a direct URL.
MIT · latest release v0.1.3 (2026-08-20)
06Frequently asked questions
How do I install dsh-design-qa?
Run `dsh plugin --profile web add dsh-design-qa`, then cd into the installed folder, set `BAILIAN_API_KEY`, and run `node install.mjs --route-only` and `node install.mjs --restart`. A working DeepSeek Harness (workspace + main model key) is required first.
Which models can read images through this plugin?
Any text-only model wired into DSH, as long as it supports tool calling — it calls `deepseek_vision` itself. The default engine is `qwen3.8-max` via Alibaba Cloud Bailian (BAILIAN_API_KEY).
Does it modify my DeepSeek Harness install?
Yes — the installer patches three files in the DSH core (auto-backed-up) so text routes accept pasted images. Uninstall with `node install.mjs --revert-patches` first, then `dsh plugin --profile web remove dsh-design-qa`.
When does the plugin retire?
It steps aside automatically once DeepSeek declares `image` in `inputModalities`: `deepseek_vision` self-rejects at runtime and the installer skips the core patch. You can keep it installed as-is.
07Related DSH workflows
modlens
by liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
agent-vision-toolkit
by anionex
Vision toolkit and skills that give text-only LLMs eyes — multi-image understanding, image Q&A, OCR, frontend UI restoration and GUI automation, with optional agent integration.
dsh-vision-router
by ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh-vision-toolkit
by anionex
为纯文本 DSH Agent 提供 10 个结构化视觉工具：意图感知图片问答、长截图 OCR、原始像素 grounding、UI 还原、像素 diff 等
08Data and sources
dsh plugin --profile web add dsh-design-qa
把识图做成一个 tool。
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-06. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.