Plugins

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Let text-only models see images: when a picture arrives with a placeholder like \[image omitted because this model accepts text only], the model calls the vision_describe tool and the plugin forwards the image reference plus the question to a multimodal model, retrying with a fallback model on failure. Configured in the settings page and persisted via the official settings API.

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Drag-and-drop / paste / upload files and images; on non-multimodal models images are auto-described by a configured VLM.

LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint, with per-model multimodal switch, fully configurable reasoning efforts, and a web settings page for editing the deployment from the frontend.

Adds an input-modality selector to custom model settings in the DeepSeek Harness Web UI.

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

Registers native doubao_generate_image and doubao_image_status Agent tools to automate Doubao Web (doubao.com) via Tabbit Browser, automatically extracting watermark-free 2.7K wm0 original images into local files and multimodal chat attachments.

An AI-native multimodal canvas for DSH: preview images, video, audio, 3D models, PDFs, documents, and code; connect ideas and collaborate with agents in a persistent local workspace.

Analyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.

Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Manage which models appear in the composer model menu. A settings page lists every provider's models with a per-model switch, provider-level show/hide, collapsible groups and filters by kind; switched-off models leave the menu while the model in use in the current session stays. The list can be searched by name or ID and filtered by capability (multimodal, reasoning) and by minimum context window (128K / 256K / 512K / 1M). Rows show the model kind, and chat models also show reasoning support with the adapter's effort levels, their context window and input modalities. Labels merge manual overrides, the settings document, the adapter, the relay's GET /models response, a built-in pi-ai / models.dev catalog, name inference and vendor corrections in that priority order, with the source named on hover and dashed borders marking inferred values. Any model can be edited by hand (kind, context window, modalities, effort levels); those edits are stored outside the profile and can be written back into the model provider's settings. A hard re-fetch drops every cache and asks the adapter and all relays again. A switch, on by default, lets relay routes whose models declare text-only input accept images in memory, without editing configuration files. The hidden list is stored in the profile patch and mirrored to $DSH_HOME.

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.

Agnes AI provider for llm-pi-ai: 4 multimodal chat models declared in the bundle patch, plus image and video generation tools.

DSV4.1 reasoning support with multimodal context and bounded artifact acceptance for DeepSeek Harness

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.