Plugins

Modellix integration for DSH: schema-driven image, video and audio generation in a split Design workspace, a live LLM model catalog, and native web search and fetch providers through one API key.

Displays CodexRadar model capability benchmarks in a Settings page and shows the selected session model's DeepSWE score beside the composer.

Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

dsh web 的 Token 用量热力图：固定近 26 周（周日起始对齐）按天着色、GitHub 风格、深色/浅色自适应；今日/本周/本月/累计四个总量 chip 点击即把明细表锁定到对应时段，可再点选单日；明细按 provider/model 拆分（输入/输出/缓存读/缓存写/占比）。数据全部来自本机会话日志，增量聚合 + 磁盘缓存。

A document preview / edit / management plugin for DeepSeek Harness. It provides a VSCode-style "Document Center" workbench inside the DSH Web GUI: a file tree on the left, click-to-preview, editable code & Markdown with Ctrl/Cmd+S save; and exposes three document tools (doc_read / doc_edit / doc_create) to agents, letting models read and write workspace documents through natural language.

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Sidebar session-title icons: an auxiliary model call on the same route as title generation draws a 24x24 monochrome SVG metaphor shown before each session row title, with disk caching.

Synchronizes the model catalog of API-key providers from the provider itself instead of maintaining the model list by hand.

Genuine Liquid Glass theme for DSH Web UI: SVG feDisplacementMap edge refraction on input card, send button, bubbles, view tabs, queue dock and sidebar. Built-in animated demo wallpaper, customizable background blur & brightness, redesigned model selector popup, glass-styled buttons throughout, and a unique water-drop settings icon.

DSH 模型检测：对任意 pi-ai 提供方，拉取其线上最新模型清单，并用 models.dev 自动富化正确模态/容量/推理后写入该提供方

Unified model routing for DeepSeek Harness: one logical ModelID over multiple providers with first-token failover and cooldown, health-aware candidate ranking, three tiers (tier1/tier2/tier3) auto-selected by purpose, per-candidate reasoning effort, and a settings-page management panel.

Skill studio for DeepSeek Harness: visualize every agent skill (name, description, source, nested flag, model/user invocation), view and edit the full SKILL.md body, toggle model/user invocation, and mine DSH session logs to extract reusable personal skills that the agent auto-loads — from the web settings panel and via skillmgr_* / skillmgr_extract_* tools.

AI-native music player plugin for DeepSeek Harness: aggregates NetEase Cloud Music, QQ Music and KuGou search with cross-provider playback fallback, renders word-by-word karaoke lyrics synced live over USB HID to HALO PIXELBAR speakers, and exposes search, playback, queue, alarm and speaker control as model tools.

An independent approval subagent judges every sandbox escalation, with a configurable model and an audit log.

Image understanding for any DSH model: vision, OCR, grounding, and crop tools with domain presets for histopathology, cell biology, anatomy, clinical images and scientific figures.

Windows desktop UI context picker for Codex, DeepSeek Harness, and MCP clients: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, and local OCR, then review and approve Markdown/JSON context before output.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

Daily news digest from 46 curated RSS sources, edited by the model already configured in dsh, delivered to your IM via webhook, and broadcast in the chat like a regular model reply with zero context cost.

DeepSeek Harness plugin: Superself's `self` CLI as model-facing tools plus a /self command — cross-session, cross-project project state for agents.

Context7 MCP bridge: gives the model up-to-date, version-specific library documentation and code examples through the Context7 MCP server, keyless by default.

Adds a subagent_routed tool that runs a one-shot subagent fully mounted on any agent preset from any session, with per-call model/provider override and a model-availability pre-check.

Windows-only computer use for DeepSeek Harness: captures the virtual screen and drives mouse & keyboard through 9 tools built on PowerShell and Win32 SendInput; pairs with picturereader so text-only models can complete the screenshot-analyze-act-verify loop fully locally.

Draft polish for the DSH composer: one-click AI polish of the input draft (sparkles button next to send), with optional conversation context and a configurable model channel.