gugu123a/dsh-tool-see-image
see_image tool for DSH: lets text-only models 'see' images by routing them to a configurable vision model (default Zhipu GLM-4V-Flash, free)
安装Install
dsh plugin --profile web add github:gugu123a/dsh-tool-see-image把 gugu123a/dsh-tool-see-image 加入你的 DSH 配置（web profile）即可启用。
READMEREADME
dsh-tool-see-image
Glad to make a plugin for #deepseekharness （or #dsh）.
Give a text-only model (e.g. deepseek-v4-flash) the ability to "see" images:
the see_image tool sends an image file to a configurable vision model
(default: Zhipu GLM-4V-Flash, free), which describes it in text; the text-only
model relays that description back to you.
How it works
You: "Look at this image" ──► Text-only model (no vision)
│ calls see_image(path, question)
▼
This plugin (Host plane)
│ 1. ctx.fs resolves & reads the image (sandbox/observation policy aware)
│ 2. encodes it as a base64 data URL
│ 3. POST {baseURL}/chat/completions (OpenAI-compatible)
▼
Vision model (GLM-4V-Flash)
│ text description
▼
Text-only model ──► reports to you
Install (DSH web profile)
Copy the plugin into your profile directory, e.g.
$DSH_HOME/profiles/web/plugins/dsh-tool-see-image/($DSH_HOMEis usually~/.dsh).Declare the dependency in
$DSH_HOME/profiles/web/package.json:"@deepseek-ai/dsh-tool-see-image": "file:plugins/dsh-tool-see-image"Then run
pnpm install(creates a junction to the source underprofiles/node_modules).Compose it into the profile in
$DSH_HOME/profiles/web/cordis.patch.yml:- insert: - id: tool-see-image name: '@deepseek-ai/dsh-tool-see-image' config: baseURL: https://open.bigmodel.cn/api/paas/v4 apiKeyEnv: ZHIPU_API_KEY model: glm-4v-flashSet your API key: create one at the Zhipu (bigmodel) console (format
id.secret), then set the environment variable (Windows example):setx ZHIPU_API_KEY "your-key"Restart your terminal, then restart
dsh web(the web profile does not hot-reload patch layers yet — tested).Verify: in a new session the
see_imagetool should appear. Try it:Use see_image to look at path/to/your/image.png
Configuration (tool-see-image line in cordis.patch.yml)
| Key | Default | Description |
|---|---|---|
baseURL |
https://open.bigmodel.cn/api/paas/v4 |
OpenAI-compatible endpoint; the plugin appends /chat/completions |
apiKeyEnv |
ZHIPU_API_KEY |
Env var name that holds the API key |
model |
glm-4v-flash |
Vision model id (free on Zhipu) |
maxTokens |
1024 |
Max output tokens. Note: glm-4v-flash caps at 1024 (higher returns 400 max_tokens参数非法; raise it if you switch to a bigger model) |
timeoutMs |
60000 |
Request timeout |
maxBytes |
15728640 (15MB) |
Per-image size limit |
prompt |
(Chinese detailed-description instruction) | Default question; the question argument takes precedence |
To use a different vision API, change these three keys, e.g. SiliconFlow:
config:
baseURL: https://api.siliconflow.cn/v1
apiKeyEnv: SILICONFLOW_API_KEY
model: Qwen/Qwen2.5-VL-32B-Instruct
Uninstall / rollback
- Remove the
- insert: ... tool-see-image ...block fromcordis.patch.yml; - Remove the junction:
Remove-Item profiles\node_modules\@deepseek-ai\dsh-tool-see-image; - Remove that line from
profiles/web/package.jsondependencies; - Restart
dsh web.
Implementation notes (for plugin developers)
- Exports
{ name, inject, Config, apply }, same shape as every DSH tool plugin; inject: ["tools", "fs"]— the tool registry and the sandboxed file service are both Host-global services;- Registered at the global layer, so every session sees it (same as TUI-mode host tool rows);
- Reads files through
ctx.fs(sandbox/observation policy applied), never rawnode:fs; - Parameter schema uses the DSH-specific format:
required: truefor required, omit therequiredkey for optional (required: falseis rejected bydefineTool); - Network request carries a timeout and
exec.signalcancellation; errors are model-readable.
Regression test
test/mount-test.mjs mounts this plugin line under a real Cordis Loader
(timer + system-prompt + tools + this plugin) and asserts that see_image
lands in the tool registry. Run:
set DSH_CHECKOUT=<your dsh install root, containing node_modules/@deepseek-ai>
node test/mount-test.mjs
Expected output: tools.schemas() 含 see_image: true and === MOUNT TEST PASS ===.
The script temporarily links the plugin into the checkout's node_modules
(Windows junction / other-platform symlink) and cleans up afterwards — no
hardcoded local paths.
Field notes
- 2026-08-13: real key +
triz-workflow.png(a DSH Web GUI screenshot) → HTTP 200 in ~6.8s, correctly read the UI text (search box / MCP settings / Fetch / Filesystem / Sequential-Thinking). - Pitfall: glm-4v-flash's
max_tokenscap is 1024 (the default of 2048 caused a 400; the default has been fixed).
Paste-to-text relay (bonus)
Beyond the see_image tool (which reads an image by path), this repo ships a
patch script that lets you paste images straight into the chat box and
have them auto-converted to text:
node scripts/patch-dsh-image-relay.mjs # apply (idempotent, auto-backup)
node scripts/patch-dsh-image-relay.mjs --check # status
node scripts/patch-dsh-image-relay.mjs --revert # rollback
pm2 restart dsh-web # then hard-refresh the browser
It patches three DSH packages (host-apiproxy, llm-deepseek, client-ui) so that:
- the UI shows the pasted image (the hidden text block is filtered out);
- DeepSeek receives a
【图片：...】description from GLM-4V-Flash instead of raw pixels; - repeated images hit a local cache (
~/.dsh/cache/image-relay/), and failures degrade gracefully within 8s.
Requires ZHIPU_API_KEY. Re-run the script after any npx dsh upgrade —
the patch is lost when the npm cache is refreshed.
License
MIT
相关推荐Related
- deepseek-ai/deepseek-harness DeepSeek Harness: Everything is a Plugin.
- deepseek-ai/deepseek-harness DeepSeek Harness (dsh) — 由 DeepSeek AI 开发的开源 agent harness（智能体框架）。一切皆插件：核心 + 插件 + 技能 = 可热插拔的 AI 编程工作台。DeepSeek Harness: …
-
nexu-io/open-design
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your…
-
ruvnet/ruflo
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build c…
-
amruthpillai/reactive-resume
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source a…
-
esengine/DeepSeek-Reasonix
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
-
volcengine/OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
-
Molunerfinn/PicGo
:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosti…