dsh-vision-pro-bridge
让纯文本 DeepSeek-V4-Pro 获得真正的视觉能力，无需新增依赖，并且仅使用 DeepSeek 路由：图像由 deepseek-v4-flash-vision-exp（您现有的 DEEPSEEK_API_KEY）进行描述，然后将文本传递给 V4-Pro。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-vision-pro-bridge@1.0.0Vision Pro Bridge 以 dsh-vision-pro-bridge 发布，当前版本为 1.0.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
点击下方 Badge 复制 Markdown，粘贴到 README 即可。
验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。
认领这个 Plugin →Give a text-only DeepSeek-V4-Pro brain real image understanding — without switching models, without Ollama, and without a second API key.
DeepSeek Harness (dsh) plugin. English · 简体中文
deepseek-v4-pro (and deepseek-v4-flash) are text-only models: their API rejects image bytes. In DeepSeek Harness, pasting a screenshot into a Pro session fails with "does not accept image input". Your only official option is to switch the whole conversation to the weaker, Flash-tier deepseek-v4-flash-vision-exp.
It registers a twin provider route — deepseek-vision-pro (model deepseek-v4-pro-vision) — that advertises image support. When you attach an image, the plugin first asks deepseek-v4-flash-vision-exp to transcribe it into text (using your existing DEEPSEEK_API_KEY), then hands that text — plus a stable local file path — to deepseek-v4-pro. The DeepSeek wire route never sees an image; V4-Pro keeps its coding brain and still "sees" the picture.
paste screenshot → [image block admitted]
→ transcribe via deepseek-v4-flash-vision-exp (text)
→ text + local path → deepseek-v4-pro answers
@deepseek-ai/dsh-llm and @deepseek-ai/dsh-llm-deepseek. No openai, no sharp, no schemastery, no Ollama.deepseek-v4-flash-vision-exp), through the same DEEPSEEK_API_KEY. No second VLM vendor, no local model, no anonymous endpoints.DeepSeekAdapter, so image normalization, Files-API upload, and inline-base64 fallback are identical to official behavior — no hand-rolled HTTP.~/.dsh/vision-pro-bridge/images/ and the stable local path is passed to the model, so V4-Pro can reference it.deepseek-v4-pro-vision: keep V4-Pro's coding ability, add vision.dsh plugin --profile web add dsh-vision-pro-bridge
# restart dsh web
Make it the default for new sessions (~/.dsh/settings.yaml):
agent-default-model:
provider: deepseek-vision-pro
model: deepseek-v4-pro-vision
Environment variables (all optional):
| Variable | Default | Purpose |
|---|---|---|
DEEPSEEK_API_KEY | credentials service | DeepSeek key (same as the official route) |
DEEPSEEK_BASE_URL | https://api.deepseek.com | Endpoint (same as the official route) |
DSH_VISION_PRO_BRIDGE_PROMPT | built-in English transcription prompt | Override the transcription prompt (e.g. Chinese UI analysis) |
Images are cached content-addressed under ~/.dsh/vision-pro-bridge/images/ (re-attaching the same image reuses the transcription); an activity log is written to ~/.dsh/vision-pro-bridge-activity.jsonl.
apply(ctx) registers a DeepSeekAdapter subclass for the provider route deepseek-vision-pro.listModels / resolveModel / prepareCall all declare inputModalities: ['text', 'image'], so the harness's image gates (paste admission, thumbnails, read_image) open. Overriding prepareCall is required — otherwise the LLM runtime projects images to placeholders before they ever reach the adapter.stream() walks every message (including nested tool-result content), and for each image block reads its bytes, saves them content-addressed, and calls super.stream() against deepseek-v4-flash-vision-exp to produce a text transcription.[图片（视觉桥分析 by …）]\n<transcription>\n\n本地路径：<path> and the now text-only conversation is streamed to deepseek-v4-pro.With no image, stream() forwards directly to Pro — zero overhead.
deepseek-v4-flash-vision-exp.DEEPSEEK_BASE_URL (not the settings-page llm-deepseek overrides).For a feature-rich take (fallback VLM chain, local Ollama, settings-page UI, image downscaling, classified errors), see dsh-vision-proxy. This plugin is the minimal, DeepSeek-only, zero-dependency version of the same idea.