DSH Market
D

Dsh Vision

by linenxi-ctrl · linenxi-ctrl/dsh-vision

InstallableBundlenpmfresh

为 DeepSeek Harness 增加外挂识图模型:圆形鲸鱼按钮、发送图片识图自动回传、模型自主截图+识图工具、多协议自动适配、小白一键安装(未装 Node.js 自动下载)

Install Dsh Vision

Clean install: prebuilt on npm and declares a `dsh.bundle` layer.

The one-line version

dsh plugin --profile my-profile add @linenxi-ctrl/dsh-vision

The easy path: this bundle is published to npm, so the install pulls a prebuilt artifact — no build step runs on your machine and no build approval is needed.

From npm — installs a prebuilt artifact, no build step on your machine

# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add @linenxi-ctrl/dsh-vision

# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config

# 3. boot the profile
dsh --profile my-profile

Package: @linenxi-ctrl/dsh-vision

Prefer to install from source instead?

From GitHub — pulls source, and may ask for build approval on first run

# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add github:linenxi-ctrl/dsh-vision#<commit-sha>

# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config

# 3. boot the profile
dsh --profile my-profile

Prerequisites

API key
Not required.
Network access
Required at runtime.
Language
JavaScript

Install check

Every field the verdict was derived from, so you can re-derive it yourself

Field checkedResultWeightWhat the spec says about it
lifecycleScriptspassinfono install-time scripts
dsh.bundlepassfatalpackage.json declares a `dsh.bundle` layer
dsh.bundle.patch filepassfatalpatch file present at `cordis.patch.yml`
npm registrypassfatalpublished as `@linenxi-ctrl/dsh-vision` — prebuilt artifacts
Verdict reason
on npm with a valid bundle declaration
package.json read
package.json
Rules applied from
docs/user/develop/basic/publish.md
Checked at
2026-08-15

From the README

Excerpt as published by the author, plain text, unedited

为 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) 增加「外挂识图模型」能力:让本来不具备视觉能力的模型,通过一个可自定义地址/密钥/提示词的外部视觉模型来「看懂」图片与屏幕。 1. **网页配置按钮与面板**:页面右下角出现一个DeepSeek 鲸鱼圆形按钮(可拖动),点击即可配置外挂识图模型的 API 地址、密钥、模型名、识图提示词(skill)、代理与超时。 2. **发送图片识图并自动回传**:点鲸鱼按钮打开面板,点「📤 发送图片」选图,插件会先把它发给外挂识图模型,等识别完成后把识别文本**自动作为消息发回当前会话**(无需手动复制粘贴),DeepSeek 基于识别文本作答。 3. **模型自己截图 + 识图**:插件为 agent 注入 `screenshot`(截屏)与 `recognize_image`(识图)两个工具,并注入提示词,模型可自行「截图 → 识图 → 等待结果」。 4. **自动适配识图 API 协议**:内置 OpenAI Chat Completions、OpenAI Responses、Anthropic Messages、Google Gemini 四种协议,并按 `apiBase` 自动探测;另有 `custom` 模板协议适配任意长尾接口。

Topics

GitHub topics on this repository

More in Text Only Vision Model

Ranked by similarity inside the cluster, not alphabetically