Plugins

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

Adds a full-screen panel to the DSH composer for writing multi-line text, movable and resizable, sharing one draft with the composer; Enter inserts a newline and only Ctrl+Enter sends, so an IME cannot turn Shift+Enter into a send.

Model picker for the DSH web composer that replaces the model seat: a search-first popup whose left column indexes the suppliers and scrolls the grouped list, with a favorites group pinned at the top, image icons separating native from bridged vision input, and a reasoning-effort panel opened from the right zone of the trigger.

Adds a reasoning-level editor with OpenAI and Anthropic protocol presets (llm-pi-ai), input-modality switches and a 1M/128K context and max-output preset to model rows in Settings.

Hebrew RTL rendering for the web GUI: any line with Hebrew reads right-to-left (messages, GenUI, question cards, the composer and input fields), and RTL-aware Cmd+Left/Right line navigation.

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

Three-tier now/next/later input planning dock for the DeepSeek Harness web GUI: a red/yellow/green priority strip replaces the busy-Enter queue, plain Enter queues to later, with in-place multi-line editing, drag reorder, and session-isolated freeze/resume; the freeze button bridges a separate plugin, [dsh-session-guard](https://github.com/drscrewdriver/dsh-session-guard) (installable from dsh-market), via stopNextTurn/resume RPC + composer lock for a real per-session lock, pairing with its global peak-hour auto-pause to stop sessions during DeepSeek's high-cost windows and resume off-peak.

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

DSH Web 输入历史插件：Ctrl+Up / Ctrl+Down 像终端一样召回与切换已发送消息，零核心改动

Bark push notifications to iPhone: turn completion, waiting-for-input, and approval events sent from the DSH Host.

Deep View: interactive views (charts, tables, inputs, answers) in any DeepSeek Harness chat

Shell-style prompt history in the DSH composer: ↑ in an empty composer recalls the previous prompt and keeps walking back, ↓ walks forward to the empty draft; history is kept per workspace, persisted across restarts and records only human input, while typing or editing a draft returns ↑/↓ to normal caret movement. Adds a Settings page to export, import and clear the history.

Desktop companion for DeepSeek Harness: a Win32 layered window that keeps a whale-girl above other applications, speaks through a bubble, comments on its own when you stay on one window for ten seconds, and answers a single question typed into a right-click input box.

Prompt optimization, next-sentence prediction, inline completion, and per-session draft stashing for the DSH input box.

Skill index browser with search, custom alias editing, and chat-input skill insertion.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

A fork of y-wi/dsh-deepseek-web that bridges the DeepSeek web client into DSH, so short-context conversations, workflows and skill packs run without an API key, and a picture pasted in DSH gets read for free. Ships a floating ball plus sidebar, one-click login that stays logged in, and a right-click action that sends any selected text into the web input after clearing it. It keeps the upstream provider id deepseek-web, so it cannot be installed next to another plugin that owns the same provider. Adapts DSH kernel 0.2.2-rc.1. Reuses your own signed-in chat.deepseek.com session (needs Chrome/Edge/Brave/Chromium or a managed browser download); this may violate DeepSeek's terms and risks rate limiting or a ban. Cannot be installed alongside y-wi/dsh-deepseek-web.

One-tap connect ModelScope language and image-generation models into DSH (off by default), with image recognition and context window filled in automatically. You can also see the free Magicube balance, jump to a model's info page, and record local call counts, trends and rate-limit events, with a usage pill beside the input box showing the balance and today's local count. All of it needs only an API key, with no account sign-in.

One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.

Comet-mode animated caret for the DSH Web composer: a glowing trail glides to the text position, with configurable accent color, thickness, trail, and a 500 ms idle blink. Extends the surface to ask-question card inputs, and fixes the caret vanishing on an empty composer or first focus, forward drag-selection not following the pointer, soft line breaks measuring against the previous line, and the caret painting outside the composer when long input scrolls. Maintained fork of Lacquervii/smooth-cursor.

DSH prompt library and reusable snippets plugin: save, edit, delete, and append prompt templates, workflow instructions, and reusable text from a button beside the composer without sending.

Feishu/Lark gateway for DeepSeek Harness with topic-persistent conversations, live execution cards, image and file inputs, in-chat approvals and questions, source allowlists, and durable one-time or recurring agent tasks created in natural language.