Introduction¶
In DSH Web, some Agents are connected exclusively to text models. When users upload images, Agents generate screenshots, browser screenshots, or reading image tools return images, the text models cannot directly perform image understanding; if image generation or editing is required, an additional image API must be integrated.
dsh-vision-mix is a vision enhancement plugin for DeepSeek Harness. It combines a text model, a vision model, and an optional image generation API into a Mix model, designed for image recognition, cross-turn follow-up questioning, image generation, and editing.
What is it¶
- Plugin Name:
dsh-vision-mix - Maintainer:
haiziyao - License:
MIT - Positioning: Vision enhancement plugin for DeepSeek Harness
- Purpose: Integrating image recognition, image follow-up, image generation, and editing capabilities into the DSH conversation flow
Mix is the model entry point registered by the plugin; it is not a standalone model service that requires a separate API Key entry. Model credentials are still managed by DSH’s Provider configuration and credential system.
Core Features¶
- Combine a text model, a vision model, and an optional image generation API into a
Mixmodel - Enable Agents that originally do not support images to recognize uploaded images, understand web page screenshots, and continuously ask about image content
- Support image generation or editing
- Detect and declare model
imagecapability in “Settings → Vision Mix” - Support testing and enabling
image - Support force-enabling
image - Support independent
OpenAI-compatibleimage generation and editing API - Support
vision_mix_image_generateto generate new images based on prompts - Support
vision_mix_image_editto edit user images or generated images that appeared in the current session - Support analyzing Agent screenshots, browser screenshots, and images returned by reading tools
- Image recognition, basic conversation, intent judgment, and image generation can use different Providers respectively
Installation and Enablement¶
Installation¶
Execute in the DeepSeek Harness repository directory:
pnpm dsh plugin --profile web add dsh-vision-mix
After installation, start Web:
pnpm dsh web
Configure Base and Vision Models¶
First, configure the models:
- Open “Settings → Models”
- Configure base model
- Configure vision model
- Image recognition, basic conversation, intent judgment, and image generation can use different Providers respectively
If image generation and editing are needed, configure an independent OpenAI-compatible image generation and editing API Provider.
Detect and Declare image Capability¶
Complete this in “Model Image Capability” under “Settings → Vision Mix”:
- Select the configured vision model
- Select “Test and Enable image” or “Force Enable image”
- If “Test” is selected, the plugin will temporarily grant the model
imagecapability - Failed tests will automatically roll back
- After successful enablement, return to “Basic Settings”
- Select base model, image model, and optional intent recognition model
- Click “Save Route”
Enable Image Generation and Editing¶
After configuring the image generation Provider, test the image generation API in “Image Generation and Editing”.
Testing the image generation API will:
- Fixed use low
- Fixed use 1024×1024
- Fixed use PNG
- Incur one actual image generation fee
- Only preview and validate the result in memory
- Not permanently write test images to attachment storage
After enabling, you can call:
- vision_mix_image_generate: Generate new images based on prompts
- vision_mix_image_edit: Edit user images or generated images that appeared in the current session
Typical Usage¶
Create a new conversation and select Mix in the model selector. The following operations belong to typical scenarios supported by this plugin:
- Upload an image and let the Agent recognize the image content
- Continue asking about specific parts or details of the image in the next turn
- Request the Agent to take a screenshot and analyze the Agent screenshot, browser screenshot, or image returned by the reading tool
- Request image generation based on a prompt
- Request editing of user images or generated images that appeared in the current session
Credentials, Attachments, and Records¶
The plugin’s credentials and record boundaries are as follows:
- The plugin does not contain or persist hardcoded API Keys
- Model calls resolve credentials via the
credential referenceof the selected Provider - Configuration is written back to the original Provider’s model profile
- API Keys are still stored in the DSH credential system
- Session records save
attachment id, not the host machine’s absolute path or image base64 vision_mix_attachment_querycan only read attachments that appeared in the current session messages, tool results, or vision recordsvision_mix_image_editcan only edit attachments that appeared in the current session messages, tool results, vision records, or generation records- Image preview validates both session id and call record id, and cannot enumerate across sessions
Default history paths:
Vision History:
$DSH_HOME/vision-mix/v1/calls/
Generation History:
$DSH_HOME/vision-mix/v1/generations/
Applicable Scenarios and Notes¶
Suitable for the following scenarios:
- Text models are already configured in DSH, and you want Agents to support uploading images, screenshots, and cross-turn follow-up questioning
- Vision models are already configured, and you need to detect and declare
imagecapability OpenAI-compatibleimage generation and editing API are configured, and you want to generate or edit images in the conversation
Notes before use:
- The plugin runs with the permissions of the current
dshprocess - Check the source code and
MITlicense before installation - Testing image capability temporarily grants
imagecapability; failures automatically roll back - Testing image generation API fixed uses
low,1024×1024,PNG, and will incur one actual image generation fee dsh-better-sidebaris not a required dependency- Core routing, image recognition, cross-turn follow-up questioning, image generation, and conversation image display remain normal even if
dsh-better-sidebaris not installed
Project Address¶
GitHub repository: https://github.com/haiziyao/dsh-vision-mix
Community directory can search by plugin name dsh-vision-mix.