Plugins

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

vision_analyze tool: analyze a local image or URL with an OpenAI-compatible vision model.

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

明眸 VisionBridge - Pont visuel développé en interne : lorsqu'un modèle aveugle reçoit une image, il appelle automatiquement un modèle visuel pour la reconnaître et renvoie le texte reconnu au modèle principal ; transparent, configurable, sans perte lors des mises à jour.

Deterministic aggregate media budgets and safe request projections for DeepSeek Harness (DSH)

Dynamic multimodal-to-text projection and cross-model vision bridge for DeepSeek Harness (dsh), allowing seamless hot-switching between vision models (Gemini/Claude) and text-only models (DeepSeek).

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

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

DSH-native video understanding with configurable multimodal providers

Plugin de revue visuelle UI/UX conversationnel pour DeepSeek Harness : outils vision_review / vision_ask adossés à n'importe quel endpoint multimodal compatible OpenAI (par ex. agnes-2.5-flash).