给 DeepSeek Harness 加眼睛和画笔:粘贴图片自动转写后继续对话,也能根据描述生成图片,模型与后端完全由用户自行配置。
- 语言
- TypeScript
- License
- MIT
- 分支
- main
安装
$ dsh plugin --profile web add github:MC5lan/dsh-multimodal在终端中运行以上命令,通过 dsh CLI 安装此插件。可在右上角切换 Profile。 第一次用 dsh?看这篇新手教程
对话式安装
帮我安装 DeepSeek Harness 插件 MC5lan/dsh-multimodal:先查看仓库 https://github.com/MC5lan/dsh-multimodal 确认安全性,然后执行安装命令并验证插件加载成功。
把这段指令粘贴给 DSH Web GUI 里的助手,由它代你完成安装与验证。
一句话定位
给 DeepSeek Harness 装上"眼睛"和"画笔":在聊天里贴图后,由你配置的视觉模型先逐字转写图片内容,再把文字交给 DeepSeek 继续解题;当对话需要出图时,可调用你配置的图片后端生成图片并直接展示在对话里。
核心能力
- 在 deepseek-vision 这条会话线路上自动启用图片附件,粘贴/拖入截图即可被识别
- 把图片转写成保留代码、报错、UI 文案的纯文字,再让 DeepSeek 在同一回合接着解题
- 提供
generate_image工具:让 DeepSeek 在需要插图时自动调用,把图片直接渲染在对话卡片中 - 提供
extract_text工具:把图片里的文字按 Markdown/纯文本/JSON 三种格式抽出来 - 支持任意 OpenAI 兼容的视觉端点(智谱、阿里百炼、讯飞星辰、硅基流动、魔搭、Ollama 等)通过配置直接接入
- 内置 0.2.1 之后的安全策略:API key 白名单、可信 host 列表、SSRF 防护、敏感字段脱敏、审计日志、LRU 缓存
技术实现
- 语言: TypeScript(ESM)
- 关键依赖: @deepseek-ai/cordis(插件注入)、@deepseek-ai/dsh-llm(注册 provider 和工具)、@deepseek-ai/dsh-settings(设置页面)、eventsource-parser(流式响应解析)
- 架构模式: Cordis 插件,通过
apply(ctx, config)在llm子系统注册deepseek-visionprovider 与用户声明的 extraProviders;同时在tools子系统注册generate_image和extract_text两个工具;在 agent pre-step 钩子中改写图像消息 - 入口文件: src/index.ts(导出
apply),src/vision.ts(视觉转写钩子),src/image-gen.ts(图生成工具),src/ocr.ts(OCR 工具)
适用场景
经常需要把报错截图、设计稿、表格、聊天记录贴进对话框让 AI 接着改、接着修,或者在写文章/做方案时希望 AI 直接生成示意图的用户。插件默认不内置任何模型,团队已有的视觉/生图服务(公司内网 API、付费平台、本地 Ollama)都可以直接接入,避免数据外传。
前置依赖与兼容性
| 依赖 | 最低版本 | 说明 |
|---|---|---|
| DeepSeek Harness | 0.1.0-rc.6 | 同时支持 web 与 headless profile |
| Node.js | 18+ | @types/node ^22.0.0,README 推荐 18 以上 |
| 平台 | 跨平台 | 无操作系统限制 |
| 原生模块 | 无 | 仅依赖纯 JS 包,无 node-gyp 编译 |
| 运行时依赖 | cordis ^4.0.1、schemastery ^3.18.1、eventsource-parser ^3.1.1 | 由插件 package.json 声明 |
安装方式
dsh plugin --profile web add github:MC5lan/dsh-multimodal
配置项
| 配置 | 类型 | 说明 | 默认值 |
|---|---|---|---|
allowedApiKeyEnvs | 字符串数组 | 允许被当作视觉 API key 读取的环境变量/凭证名 | ["DEEPSEEK_API_KEY"] |
trustedBaseUrls | 字符串数组 | 除官方主机外,额外允许的视觉 API baseURL(含本地 Ollama) | [] |
providers.deepseek.baseURL | 字符串 | DeepSeek API 地址 | https://api.deepseek.com |
providers.deepseek.apiKeyEnv | 字符串 | DeepSeek API key 对应的环境变量/凭证名 | DEEPSEEK_API_KEY |
providers.deepseek.models | 数组 | 在 deepseek-vision 路由下额外展示的模型列表 | [] |
extraProviders.<key> | 对象 | 任意 OpenAI 兼容视觉端点(含 displayName/baseURL/apiKeyEnv/models) | {} |
vision.watchProvider | 字符串 | 启用"眼睛"的会话线路 | deepseek-vision |
vision.transcribeProvider | 字符串 | 真正做视觉转写的 provider(留空 = 关闭转写) | "" |
vision.transcribeModel | 字符串 | 转写使用的模型 ID(留空用路由默认) | "" |
vision.fallbackProviders | 字符串数组 | 主视觉 provider 失败/限流时按顺序尝试的备选 | [] |
vision.transcribeMode | 字符串 | 转写模式:auto/structured/ocr/describe/error-fix/chart-sql/design-code | auto |
vision.parallelImages | 布尔 | 多张图片是否并发转写 | false |
vision.costProvider/costModel/costMaxPixels | 字符串/数字 | 小图走廉价 provider 的成本路由(≤ N 像素) | ""/""/1000000 |
vision.sceneHints | 布尔 | 是否在截图转写后追加场景提示 | true |
vision.redactSensitive | 布尔 | 是否在转写结果中脱敏手机号/身份证/邮箱 | false |
vision.auditLog | 布尔 | 是否为每次转写打一行审计日志 | false |
vision.transcribePrompt | 字符串 | 发给视觉模型的转写指令 | 内置"逐字转写"长 prompt |
vision.transcribeTimeoutMs | 数字 | 单次转写超时(毫秒) | 90000 |
ocr.provider/ocr.model | 字符串 | extract_text 工具使用的 provider 与模型 | "" |
image.backends.<key> | 对象 | 图生成后端定义(kind/baseURL/apiKeyEnv/model/defaultSize) | {} |
image.activeBackend | 字符串 | 当前激活的图生成后端 key(留空 = 关闭出图) | "" |
image.failoverOrder | 字符串数组 | 主后端失败时按顺序回退的后端 key 列表 | [] |
image.verifyChineseText | 布尔 | 是否用视觉模型二次校验生成图片里的中文是否乱码 | false |
image.verifyProvider/verifyModel | 字符串 | 校验用的视觉 provider 与模型 | "" |
streamIdleTimeoutMs | 数字 | 流式响应空闲超时(毫秒) | 300000 |
常见问题
Q: 这个插件自带模型吗?
A: 不带。插件只提供接入逻辑和 UI,真正的视觉模型(智谱、硅基流动、魔搭、讯飞星辰、本地 Ollama 等)和图生成后端(阿里百炼、OpenAI 协议、自定义适配器)都需要在设置页面或配置文件中自行声明,详见 extraProviders 与 image.backends。
Q: 图片字节会上传到 DeepSeek 吗?
A: 不会。dsh-multimodal 在请求发送给 DeepSeek 之前,先用你配置的视觉模型把图片转写成文字,原始图片字节始终留在本地或你选的视觉服务商,不会进入 DeepSeek 的上下文。
Q: 视觉识别和图生成能接本地 Ollama 吗?
A: 可以。设置 → 多模态 → 平台接入里有"本地 Ollama"一键预设,自动把 http://localhost:11434 加入可信 host 列表,本地回环地址无需 API key。
Q: 怎么避免误把别的密钥当作视觉 API key 发出去?
A: 0.2.1 起插件维护了一份 API key 白名单(allowedApiKeyEnvs)与可信 host 列表(trustedBaseUrls):只有白名单里的环境变量名才允许被读作 API key,base URL 必须命中已知官方 host 或可信列表;本地回环地址单独放行。
Q: 后端生成图片失败会怎样?
A: 你可以在 image.failoverOrder 配置备选后端顺序,主后端请求失败时会按顺序回退;AUTH 类错误或用户主动中止则不触发回退,避免浪费额度。
Q: 没有视觉 provider 时粘贴图片会怎样?
A: 会以占位符 【图片转写失败: 原因】 注入到对话,DeepSeek 会继续解题而不是卡住;如果你不希望图片出现,关掉 vision.transcribeProvider 即可。
Q: 设置里没有"多模态"入口怎么办?
A: 先确认插件已挂载(dsh --profile web --dump-config 应列出 dsh-multimodal),然后在浏览器硬刷新(Ctrl+F5)。
Q: 怎么卸载/禁用这个插件?
A: dsh plugin --profile web remove 即可卸载(GitHub 安装对应 remove github:MC5lan/dsh-multimodal),卸载不影响你已经写好的 ~/.dsh/settings.yaml 中 dsh-multimodal 段,下次再装会自动恢复。
上手难度
入门 — 配置项看似多,但 README 把"贴 key → 用"做成了一键流程,平台预设卡和 paste-key 自动识别都默认开启,没有视觉模型时也不会让对话卡死。
已知问题与限制
- 自定义图片后端(
kind: custom)通过import()动态加载用户提供的.mjs文件,该文件以宿主进程的全部权限执行,README 与源码均明确提示"只加载你信任的文件" - 远程 extra provider 必须使用 HTTPS 且 host 命中官方/可信名单;只有本地回环(localhost/127.0.0.1/[::1])才允许走 HTTP 且免 key
kind: custom的图生成后端必须在配置里显式声明adapterFile,否则validateConfig会拒绝加载- 用户声明的视觉 provider 默认没有
name/description/contextWindow时,注入到模型目录会回退为 128k 上下文,但maxTokens没有默认值(避免被当成真实值),需要在配置里显式提供 - 视觉转写失败时会以占位符继续对话而不会重试,因此依赖稳定视觉 provider 时建议在
fallbackProviders配置至少一个备选
English | 简体中文
Give DeepSeek a pair of eyes and a paintbrush: paste a screenshot or image into the conversation and the vision provider you configured first transcribes it verbatim (error messages, code, UI text preserved), then DeepSeek keeps solving your problem — all in the same turn, no extra steps. When an illustration is needed, DeepSeek automatically calls the image backend and the generated pictures appear right in the conversation.
Blank slate by design: this plugin ships no built-in models, providers, or backends. Vision endpoints, image backends, and models are all declared by you — plug in whatever API you already have (DeepSeek, Zhipu, Aliyun, SiliconFlow, ModelScope, Xfyun, Qianfan, local Ollama, …). Nothing is preloaded, nothing is assumed.
Compatibility: built for DeepSeek Harness
0.1.0-rc.6(Web and headless). See CHANGELOG.
Features
| Scenario | Behavior |
|---|---|
| Plain-text chat | Straight to the DeepSeek API (unchanged) |
| Image + question (e.g. error screenshot) | Your configured vision provider "looks" first → transcribes to text → DeepSeek continues from the transcription (fix code, explain, propose); hitting "stop" aborts the vision call immediately |
| Attaching an image | No more "current model does not support images" |
| User asks for an image | DeepSeek calls generate_image → the configured image backend produces pictures shown in the conversation; backend failover tries the next backend if the active one fails (AUTH/aborted skips failover — no wasted quota) |
| Any image API | A custom backend plugs any non-OpenAI/DashScope API in via a small adapter file — no plugin code changes |
| Image card | Dedicated generate_image card: thumbnail grid, click-to-zoom lightbox, one-click download, prompt & model metadata, crop-to-ask (drag a region + ask), copy params (reproducible JSON), retry button on failure (refine-aware) |
| Extracting text from an image | DeepSeek can call extract_text (OCR) → Markdown / plain text / JSON; decoupled from the watch route, usable in any session |
| Paste-key auto-connect (0.7+) | Paste any API key into the quick-add box → platform auto-detected (key fingerprint → /models probing) → endpoint + allow-list + credential + model list + feature enablement in one step |
| Vision platforms | extraProviders accepts any OpenAI-compatible vision endpoint + one-click preset cards (Zhipu, Bailian, Xfyun, ModelScope, SiliconFlow, Qianfan, local Ollama) |
| Transcription cache | Same image + same context reuses the previous transcription — no wasted vision quota (LRU, per-session) |
| Vision fallback chain | Primary vision provider rate-limited/failing → automatic switch to fallbackProviders |
| Parallel transcription | parallelImages transcribes each image in its own concurrent call (fast multi-image turns) |
| Scene modes | Built-in transcribeMode presets: error-fix (error-screenshot diagnosis), chart-sql (chart → SQL + Pandas), design-code (design mockup → HTML+CSS) |
| Cost routing | Small images (≤ costMaxPixels) automatically go to a cheap provider |
| Local vision | One-click Ollama preset keeps sensitive images off the network (see Local vision models) |
| Config migration | Settings page exports/imports the whole config as JSON (allow-listed fields only) |
Security
Since 0.2.1, the plugin hardens itself against malicious or hand-edited configurations:
- API key allow-list (
allowedApiKeyEnvs): only listed env/credential names may be read as an API key — a malicious config can no longer nameGITHUB_TOKEN(or any other secret) asapiKeyEnvto exfiltrate it - Trusted base URLs (
trustedBaseUrls): custom vision providers must target official hosts or hosts you explicitly allow — credentials cannot be silently redirected to an attacker endpoint; explicitly listed local endpoints (e.g.http://localhost:11434) are allowed over plain http and need no key - SSRF guard: generated-image downloads and
reference_imageURLs refuse loopback / private (RFC1918) / link-local addresses - No sessionId forwarding: internal harness session ids are never sent to third-party vision APIs
- Prompt-injection markers: vision & OCR outputs are wrapped in explicit "untrusted context" markers before being handed to the text model
- Sensitive-data redaction (
redactSensitive): phone numbers / 18-digit IDs / emails are masked in transcriptions (including cache hits) - Audit log (
auditLog): one line per transcription with time / image count / bytes / latency / provider - Bounded memory: transcription cache, per-session image recall, and image-kind stats are all LRU-capped — no unbounded growth
Installation
Prerequisites: official DeepSeek Harness (0.1.0-rc.6+) installed and running, Node.js 18+.
# Option 1: install straight from the GitHub repo (requires git)
dsh plugin --profile web add https://github.com/MC5lan/dsh-multimodal
# Option 2: clone and install from a local path
git clone https://github.com/MC5lan/dsh-multimodal.git
dsh plugin --profile web add /path/to/dsh-multimodal
# Also add for headless mode when needed:
dsh plugin --profile headless add /path/to/dsh-multimodal
The repo ships prebuilt artifacts (lib/), so you can install right after cloning; to rebuild from source, see Development.
After restarting dsh web, a 「多模态 / Multimodal」 page appears in the Settings sidebar — everything is configured in one place:
- Status bar (one row): 识图 ✓/✗ · 画图 ✓/✗ — computed from real capability (transcription provider set AND registered / backend exists AND active), so it never shows "configured" when the feature is actually off
- 快速接入 (quick add): the paste-any-key auto-detect box is front and center — paste an API key, the plugin figures out the platform (key fingerprint match first, then
/modelsprobing against known endpoints; key travels one-shot, never stored), and one step later the endpoint is registered, the key env allow-listed, the credential stored, the model list pre-filled, and 识图/画图 enabled. Works with any OpenAI-compatible API. Below it: platform preset cards (Zhipu, Bailian, Xfyun, ModelScope, SiliconFlow, Qianfan, local Ollama) and a custom-endpoint form - 已接入 (connected, open by default): platforms with editable model chips + image-backend management (switch / remove / add form)
- 高级 (advanced, collapsed): the two KeyCards (视觉转写 Key / 图像生成 Key), vision details (watch route, transcription provider, mode, four toggles), and config export/import
Everything in the common path is: paste key → done. The picker then shows
deepseek-vision models (e.g. DeepSeek-V4-Flash (Vision)) — that route's
sessions get the "eye".
Usage
- Fastest path (recommended, 0.7+): Settings → Multimodal → 快速接入 → paste your API key — platform auto-detected and connected in one step (endpoint + allow-list + credential + model list; 识图/画图 enabled automatically). If the key can't be recognized, the hint says why; then pick a platform card or use a custom endpoint.
- Manual path: tap a preset card (Zhipu / Bailian / Xfyun / ModelScope / SiliconFlow / Qianfan / local Ollama) and paste the key, or declare any OpenAI-compatible endpoint in
extraProviders; optionally fillproviders.deepseek.modelsto advertise models on the built-in DeepSeek route slot. - In the Web UI model picker choose a
deepseek-visionmodel — that route's sessions get the "eye". - Chat normally; paste/drag an image and ask to have it read, or just say "draw me a …" to generate one.
API Keys (or write the credentials file directly)
The Settings → Multimodal → 密钥管理 page writes both keys for you. To edit
the credentials file directly (path is $DSH_HOME/.credentials.yaml, default
~/.dsh/.credentials.yaml), it takes effect immediately:
VISION_API_KEY: <your-vision-endpoint-key> # vision transcription (see 视觉转写 Key in the UI)
IMAGE_API_KEY: <your-image-backend-key> # image generation (see 图像生成 Key in the UI)
These are your provider keys — any OpenAI-compatible endpoint you register in 平台接入 accepts its key under the env name you give it (
apiKeyEnv).
How it works
User image ──▶ host admission (model directory declares image modality → allowed, no popup)
──▶ agent/pre-step (plugin): detects images → configured vision engine transcribes
└─▶ image blocks replaced by "【图片内容转写】…" text
──▶ DeepSeek API processes the transcription + your question (image bytes never reach DeepSeek)
- The
deepseek-visionroute is the DeepSeek API with a directory that advertises image support so the UI allows attachments — images are actually transcribed by the provider you configured, never sent to DeepSeek - Image bytes are read through the dsh attachment service; the transcription instruction defaults to "transcribe verbatim + extract key error info" and can be customized in the
dsh-multimodal:section of~/.dsh/settings.yaml - On transcription failure it degrades to a
【图片转写失败: 原因】placeholder — DeepSeek keeps going instead of hanging - Settings UI: Settings → Multimodal (
settings.sectionslot, native look & feel like the Models page)
Configuration (optional, ~/.dsh/settings.yaml)
dsh-multimodal:
# 0.2.1+ security: only these env/credential names may be used as API keys
allowedApiKeyEnvs:
- DEEPSEEK_API_KEY
# - MY_PROVIDER_API_KEY # add your custom provider's key env here
# 0.2.1+ security: extra vision hosts allowed to receive credentials
trustedBaseUrls:
# - https://my-vision.example.com # add your custom provider's host here
providers:
deepseek:
models: [] # optional: advertise models on the DeepSeek route slot
vision:
watchProvider: deepseek-vision # sessions on this route get the "eye"
transcribeProvider: '' # the provider that "sees" (blank = transcription off)
fallbackProviders: [] # 0.2.2+: providers tried in order when the primary rate-limits/fails
transcribeMode: auto # auto | verbatim | structured | ocr | describe | error-fix | chart-sql | design-code
parallelImages: false # 0.2.5+: transcribe each image in its own parallel call
costProvider: '' # 0.2.5+: cheap provider used for small images (cost routing)
costModel: ''
costMaxPixels: 1000000 # images ≤ this many pixels go to costProvider
sceneHints: true # 0.2.5+: append diagnosis hint to screenshot transcriptions
customModes: {} # 0.2.4+: custom mode name → prompt pairs (plugin-in transcribers)
redactSensitive: false # 0.2.4+: mask phone/ID/email in transcription output
auditLog: false # 0.2.4+: log a line per transcription (time/images/bytes/ms/provider)
ocr:
provider: '' # OCR tool engine (blank = disabled; any registered vision provider works)
model: ''
image:
backends: {} # add backends in the UI; nothing is preloaded
activeBackend: '' # image backend key (blank = no image generation)
failoverOrder: [] # 0.2.5+: backend keys tried in order when the active backend fails
verifyChineseText: true # 0.2.3+: check generated Chinese text for garbling via a vision model
verifyProvider: '' # vision provider used for the garbling check (blank = check disabled)
transcribePrompt: ... # custom transcription instruction
transcribeTimeoutMs: 90000 # transcription timeout
# Any OpenAI-compatible vision platform (just add the key; shows up in the model picker & Models page)
extraProviders:
xfyun-vision: # Xfyun MaaS
displayName: 讯飞星辰视觉
baseURL: https://maas-api.cn-huabei-1.xf-yun.com/v2
apiKeyEnv: XFYUN_API_KEY
models:
- id: xoppaddleocrv16 # free OCR (PaddleOCR-VL-1.6)
name: PaddleOCR-VL-1.6
siliconflow-ocr: # SiliconFlow (free hosted DeepSeek-OCR)
displayName: 硅基流动 OCR
baseURL: https://api.siliconflow.cn/v1
apiKeyEnv: SILICONFLOW_API_KEY
models:
- id: deepseek-ai/DeepSeek-OCR
name: DeepSeek-OCR
modelscope-vision: # ModelScope (2000 free calls/day)
displayName: 魔搭视觉
baseURL: https://api-inference.modelscope.cn/v1
apiKeyEnv: MODELSCOPE_API_TOKEN
models:
- id: Qwen/Qwen3-VL-8B-Instruct
name: Qwen3-VL-8B
Image backends (OpenAI-compatible /images/generations and DashScope protocols) example — add them in the UI or write them here:
dsh-multimodal:
image:
backends:
z-image: # Aliyun Z-Image family (new multimodal-generation sync protocol)
kind: dashscope-v2
baseURL: https://dashscope.aliyuncs.com
apiKeyEnv: DASHSCOPE_API_KEY
model: z-image-turbo
defaultSize: 1024*1024 # supports 512*512 ~ 2048*2048
modelscope-t2i:
kind: openai-images
baseURL: https://api-inference.modelscope.cn/v1
apiKeyEnv: MODELSCOPE_API_TOKEN
model: <a lightning-badged text-to-image model in the ModelScope plaza>
activeBackend: z-image
Custom image backends (0.2.6+)
Anything that is not OpenAI-compatible or DashScope can be plugged in with a
small adapter file — no plugin code changes. Write an ES module exporting a
default object with a generate() function:
dsh-multimodal:
image:
backends:
my-api:
kind: custom
adapterFile: D:/my-adapters/my-api.mjs # absolute or relative path
baseURL: https://api.example.com/v1 # passed to the adapter
apiKeyEnv: MY_API_KEY
model: my-image-model
defaultSize: 1024*1024
activeBackend: my-api
failoverOrder: [z-image] # fall back to another configured backend
The adapter receives { prompt, size, n, negative_prompt, reference_image, apiKey, baseURL, model, signal, fetch, log } and returns
{ urls: string[], b64s: string[] }. See
scripts/adapters/example-custom.mjs
for a template. Only point adapterFile at files you trust — the adapter
runs with full process privileges. Polling backends can tune
pollIntervalMs / pollTimeoutMs per backend.
Local vision models (keep sensitive images on your machine)
The plugin routes transcription through any OpenAI-compatible endpoint, so a local
Ollama vision model keeps image data off the network. One-click
preset: Settings → Multimodal → 平台接入 → + 本地 Ollama (auto-adds
http://localhost:11434/v1 to trustedBaseUrls; local endpoints need no API key).
Model matrix (pick by VRAM):
| Model | ollama pull | VRAM | Notes |
|---|---|---|---|
llava | ollama pull llava | ~4 GB | Classic 7B, good OCR-ish |
llava-llama3 | ollama pull llava-llama3 | ~6 GB | Stronger baseline |
qwen2.5vl:7b | ollama pull qwen2.5vl:7b | ~6 GB | Better Chinese text |
minicpm-v | ollama pull minicpm-v | ~6 GB | Document/OCR focused |
qwen2.5vl:32b | ollama pull qwen2.5vl:32b | ~20 GB | High quality, big VRAM |
Compare providers before wiring them in:
node scripts/benchmark-vision.mjs shot.png \
my-endpoint=https://your-vision-api.example.com/v1,your-model,YOUR_API_KEY_ENV \
ollama=http://localhost:11434/v1,llava,SKIP
Troubleshooting
| Symptom | Cause & fix |
|---|---|
| Reply says "【图片转写失败: MISSING_CREDENTIAL…】" | Vision key missing: add it under Settings → Multimodal → 密钥管理, or write the credentials file |
| Reply says "【图片转写失败: RATE_LIMIT…】" | Free-tier rate limit; retry later or switch to a paid tier |
| Transcription is off (images ignored) | vision.transcribeProvider is blank — set it to a registered provider in Settings → Multimodal → 视觉转写 |
| No "Multimodal" entry in Settings | Verify the plugin is mounted (dsh --profile web --dump-config should list dsh-multimodal) and hard-refresh the browser (Ctrl+F5) |
| Custom vision provider skipped with a "not trusted" warning | Its base URL isn't allow-listed: add it to trustedBaseUrls (or use one of the official hosts); also make sure its key env is in allowedApiKeyEnvs |
Development
npm install
npm run build # host: tsc; client: tsc check + tsdown builds lib/client.js
License
查看使用指南 →
该插件的安装步骤、关键要点、FAQ 与兼容性说明(基于已收录字段派生)。
收录徽章
[](https://deepseek-plugin.org/plugins/MC5lan/dsh-multimodal)把这段 markdown 粘贴到你的 GitHub README,链接回本插件详情页。徽章只声明已被本站收录,不代表安全认证。