Plugins

Template-driven code review skill: five-step review flow, critical/medium/minor severity grading, four-dimension scoring (quality, security, performance, maintainability), dual text and HTML report output, and an on-demand reference knowledge base.

Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

Voice-announce the final reply on Windows (SAPI5 natural voices) and macOS (system voice); skips reasoning and tool calls, one-line npm install.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Free vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.

Tavily search with multiple API keys, key rotation and failover, a usage gauge, and a settings card.

A web-novel writing engine for DeepSeek Harness: parallel drafting, outlining and brainstorming with a separate DeepSeek key, lore and foreshadowing management, semantic vector retrieval, a corpus library, usage ledger, mechanical proofreading, and a local serialization plan.

Route eligible shell commands through rtk to compress tool output and save tokens.

Expert-mode agent preset for DeepSeek Harness (v0.6.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. Features: Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (28% token savings), expert persistence, cross-expert communication protocol, cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Honcho memory bridge: auto-syncs every conversation turn to a self-hosted Honcho service, with recall/search/remember/context/status tools, context injection on session start, and a visual settings panel.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Archived Chats settings page for DeepSeek Harness: browse, search, filter, tag, annotate, measure storage, export and preview-first import of versioned JSON/Markdown ZIP backups, restore non-conflicting archives, unarchive, and delete sessions by workspace, including live sessions without a restart.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Web theme and file workspace plugin with global typography controls, @file mentions, a project file tree, Markdown preview, and a resizable side panel.

Use wallpapers downloaded in Wallpaper Engine as the DeepSeek Harness web background: video wallpapers play in place, image wallpapers use the highest-resolution standalone artwork, with cover/contain fit modes and a 0-100 panel dimmer.

IKUN fandom skin for the DSH Web UI: star-blue and black-gold palettes in the system theme list, full-screen photo wallpaper rotation, a music box, and a send-button voice line.

All-in-one bundle for DSH: the native Windows desktop window (WebView2), DeepEye vision (GLM-4V-Flash), and voice input (mic button) in a single install.

Real-time 'We need…' and 'Let me…' reasoning-trajectory keyword stats for the DeepSeek Harness web chat.

Live-tune the DSH Web conversation UI from Settings: message font size, Claude Desktop-style markdown tables, dialog width, an optional timeline rail, and a GitBar with branch management, per-file diff, and commit & push.

Left-edge user-Turn navigation rail with reading-position highlighting, hover previews of per-turn metrics and model-answer excerpts, keyboard and click-to-jump controls, and local conversation search.

Standalone workspace file-tree panel for the DSH web UI: a session-header icon opens an animated popup of the current workspace tree; click or drag a file to insert its reference into the composer, with search, inline preview, live settings, and zh/en i18n; single-purpose, zero-config, one-command install.

Visual GitHub login without a terminal: in-window device flow, token synced into the gh CLI, and host status/launch endpoints.