dsh-minimax-multimodal: Providing MiniMax Multimodal Capabilities for DeepSeek Harness (DSH)
The `dsh-minimax-multimodal` plugin is designed for DeepSeek Harness (DSH) to integrate MiniMax's multimodal capabilities—image understanding, generation, speech synthesis, and transcription—into DSH workflows. It provides multiple tools supporting text-to-image generation, speech synthesis, and audio transcription, with generated content automatically registered as deliverables. Installation requires adding the local directory via the CLI and configuring the `MINIMAX_CN_API_KEY`. When using it, note the file size limits and environment dependencies.
Read MoreDeepSeek Harness Vision Bridge Plugin
`dsh-vision-bridge` is a vision plugin designed for DeepSeek Harness (DSH), aiming to compensate for the limited image-processing capabilities of text-only models. The plugin supports configuration through a GUI or YAML, allowing users to choose a DSH provider or a custom OpenAI-compatible API. Its core features include: enabling models to proactively invoke the `vision_bridge_read_image` tool for OCR and semantic analysis; automatically uploading images pasted into the input field and generating reference markers; and providing connectivity testing and visual configuration. It is compatible with DSH 0.1.1+ and enables the flexible construction of vision agents by reusing existing channels or using standalone configuration.
Read MoreDeepSeek Harness Plugin: dsh-vision-plugin
The dsh-vision-plugin for DeepSeek Harness resolves the cumbersome issue of manually describing images in multimodal conversations by automatically generating a description of image content before a message is sent and injecting it into the message. The plugin supports uploading or pasting images and uses DashScope vision models or Windows offline OCR to parse them. Users can select an OCR-only or vision-based description mode in the chat box; after a successful description, the system automatically inserts the description at the beginning of the message. The plugin follows a strict routing policy, processes images in memory as base64, and never writes them to disk. This tool simplifies multimodal interaction workflows and is suitable for developers.
Read MoreIntroduction to the DSH Multimodal Plugin
The `dsh-multimodal` plugin is designed to address the limitation in DeepSeek Harness (DSH) where native text models cannot process images or other non-text files. It intercepts inputs before the session model and, through a separately configured processing model chain, converts images, videos, and audio into text descriptions before further processing. It supports preset management, intelligent fallback, custom prompts, and file size limits. Users can install it via the CLI and enable it in the settings to submit multimodal content by pasting, dragging and dropping, or specifying attachment paths. The plugin also provides flexible failure-handling strategies and a text-native passthrough capability.
Read Moredsh-design-qa: Enabling Image Understanding for Text-Only Models in DeepSeek Harness
The dsh-design-qa plugin enables text-only models to “read” images by integrating multimodal tools, allowing them to perform visual judgments within the product design loop. It supports on-demand invocation, does not consume the main model's context, and includes built-in evaluation benchmarks. Installation requires configuring an Alibaba Cloud Bailian API Key, and it defaults to using the qwen3.8-max model. The plugin emphasizes that “visibility does not equal judgment capability” and should be used according to specific scenarios.
Read More