dsh-visual-plugin
Adds an OpenAI-compatible vision bridge to DeepSeek Harness, forwarding images to a configured vision model and displaying descriptions in a web panel.
Install
$ dsh plugin --profile web add dsh-visual-plugin # or: github:jyh20030112/dsh-visual-pluginRepository Intelligence
AI-assisted, source-grounded explanation based on the public repository snapshot. It does not replace compatibility or security verification.
Key Capabilities
- Recursively detects uploaded images and image-bearing tool results for description.
- Forwards images and intent-aware prompts to a configurable OpenAI-compatible vision model.
- Provides a vision_describe tool for follow-up image questions.
- Adds a web right-side panel for endpoint, model, and API-key configuration, connection testing, recent descriptions, thumbnails, and remaining balance.
- Keeps the vision API key in the Harness credentials seam and does not echo it.
- Degrades failed or unconfigured vision calls to a placeholder so the conversation continues.
Useful For
- Give a text-only DeepSeek Harness model image-description context.
- Ask a vision model targeted questions about uploaded images.
- Inspect recent image descriptions and thumbnails from the web UI.
- Use an OpenAI-compatible vision endpoint with DeepSeek Harness.
Who It Fits
- DeepSeek Harness web users with a text-only primary model.
- Users operating an OpenAI-compatible vision API endpoint.
- Developers who want a host-and-browser vision integration for DSH.
Documented Limitations
- Requires configuration of an endpoint URL, vision model name, and API key.
- The main model receives generated text descriptions rather than native image understanding.
- The documented setup targets the DSH web profile and requires restarting dsh web.
- Unconfigured or failed vision calls produce a failure placeholder instead of a description.
- Building from source requires a local DeepSeek Harness checkout, although prebuilt lib artifacts are committed for consumers.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 23 development, 13 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 23 development, 13 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 21 development, 11 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 21 development, 11 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Public GitHub source metadata is available for this registry snapshot.
package.json declares 0 runtime, 21 development, 11 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
A root package.json was captured and can be inspected by the registry.
GitHub reports the repository license as MIT.
Source & Registry Notes
Traceable source and registry metadata for this entry, kept separate from runtime verification.
- Source repository
- jyh20030112/dsh-visual-plugin
- Registry source
- Public GitHub repository
- Source snapshot
- e69c903aea15
- Artifact type
- plugin
- AI enrichment
- gpt-5.6-terra · 2026-08-14
- Prompt version
- dsh-plugin-enrichment-v3
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 4
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-08-14
- Last release
- 2026-08-14
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Loops (auto-research) and more. #dsh
View plugin →Persona-driven UX walkthrough plugin for DeepSeek Harness (DSH) - scans React + TypeScript source code for UX issues, pinpoints them, and suggests fixes.
View plugin →DeepSeek Harness vision-routing plugin with provider fallback chains and pixel-level image tools.
View plugin →DeepSeek Harness plugin that reviews risky tool calls with a stronger model and adds a BlockRun x402-paid LLM provider route.
View plugin →