Plugin

Registra una route provider `deepseek-vision`: la GUI web accetta immagini incollate e le trascrive in testo tramite la free Zhipu GLM vision API prima di delegare all’adattatore DeepSeek.

Le immagini allegate nel composer vengono trascritte in testo da un modello di visione compatibile con OpenAI prima di raggiungere i modelli DeepSeek solo testo

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in free vision model and automatic rate-limit failover.

Plugin di routing a due modelli per DSH: la conversazione principale resta su DeepSeek, le attività con immagini vengono distribuite automaticamente al modello di visione configurato esplicitamente e il risultato dell'analisi torna a DeepSeek per proseguire.

Plugin DeepSeek Harness: una rotta `deepseek-vision` che dichiara l'input di immagini e trascrive le immagini incollate tramite i modelli di visione gratuiti Zhipu GLM prima di delegare all'adattatore DeepSeek.

Visione per qualsiasi rotta DSH: incolla immagini nel compositore web con analisi automatica guidata dall'intento, delega la lettura delle immagini dello spazio di lavoro a un subagente di visione Kimi/MiniMax e materializza gli originali incollati per modificarli.

Instrada le immagini della chat verso un modello di visione fisso compatibile OpenAI, restituisce osservazioni fattuali al modello principale selezionato e riusa le osservazioni per sessione attraverso replay, compattazione e riavvii.

Xiaomi MiMo-powered voice for DeepSeek Harness: browser 🎤/🧠/🔊 UI, voice_transcribe/voice_understand/voice_speak tools, configurable voice map (preset/voicedesign/voiceclone). Fork of zhuiyueya/dsh-voice (MIT), Settings pattern from Anionex/dsh-vision-toolkit (MIT).

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

Display companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.

DeepSeek Harness plugin: a vision worker over Cloudflare Workers AI (@cf/moonshotai/kimi-k2.6) that routes image requests from text-only callers, returns a versioned righthand.vision.v1 envelope, and supports follow-up questions.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

DSH Web 插件：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + 插件设置卡片）。

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.

DeepSeek Harness OCR plugin — offline image text recognition powered by PaddleOCR-json (primary) and RapidOCR-json (fallback). 让 DeepSeek Harness 直接识别图片中的文字，无需视觉模型、完全本地离线运行。

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

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.

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.