プラグイン

Native dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into <vision-context> via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.

FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

DSH tool plugin: generate images through ToAPIs async GPT-Image-2 API (submit task, poll, download).

Save messy notes (text + images) to a Yuque knowledge base, classified by the model.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Lets a text-only DeepSeek agent read images in the same session by delegating to a vision-capable subagent, with send-time image-to-path conversion.

Windows組み込みエンジン(Windows.Media.Ocr)による添付画像のローカルOCR:モデルに送信されるのは認識されたテキストのみで、画像バイトは送信されません。ビジョンパススルーはオプトインです。

Tesseract による添付画像のローカル OCR。認識されたテキストのみを model に送り、画像バイト列は送らない。vision passthrough は任意。

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

Observational file-mutation rollback for the fs tools: write/edit pre-images are checkpointed as git blobs or snapshots and restored through a model-facing rollback_files tool or a /rollback command.

Upload files and folders straight into the conversation — images attach as real message blocks, text content is written into the composer draft, folders land by directory structure.

NanoBananaPro API を通じて、DeepSeek Harness で画像と動画を生成できます。

Seedance 2 AI API を通じて、DeepSeek Harness で画像と Seedance 動画を生成できます。