dsh-plugin-chat-enhance
Run the following command in DeepSeek Harness:
dsh plugin install supanexus/dsh-plugin-chat-enhance
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness: dsh plugin install supanexus/dsh-plugin-chat-enhance; source URL https://github.com/supanexus/dsh-plugin-chat-enhance.
About this plugin
As your model roster grows, swapping between providers, filtering by capability, and guessing which ones accept images becomes a small daily annoyance. This plugin pulls those micro-tasks right next to the chat input, so picking the right model and attaching the right image takes two seconds instead of a context switch to some other panel.
Open the model picker and you can search by name, filter by provider, or flip on a one-click view that shows only image-capable models. Your most recently used model sits right beside the input bar, one click to switch back. When you need vision support, a small badge next to the model name makes it instantly obvious who handles images. To actually send one, hit the paperclip on the left of the input, drop the file into the current draft, and send — all without ever leaving the conversation.
Built for users juggling models from multiple providers and switching mid-conversation, or anyone who wants multimodal messaging to feel as natural as plain text. Model search and switching work standalone without SupaNexus Core; the image badge and upload stay gracefully disabled until the active model declares image-input support, so the rest of the plugin keeps working either way.
Use Cases
- Quickly search and switch between models from multiple providers
- Send a local image directly to a vision-capable model in the chat
- Filter models by provider or image support to match the current task
Best For
- dsh users who frequently switch between models from multiple providers
- Users who want multimodal interaction as smooth as plain-text chat
- Users who prefer to finish model selection and image sending in one input bar
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.