Plugins

Registers a local LLM provider that routes model calls to an OpenAI-compatible endpoint or the Ollama native API, with a connection-test card in the Models settings page and no account sign-in.

Reads each third-party endpoint's own model listing and keeps llm-pi-ai's per-model reasoningEfforts in sync, so the composer offers the thinking levels a model actually has.

Model routing groups for the session model picker: bind a group to a session, and once a model exhausts every retry policy the plugin records the failure with its error code, switches to the next usable model in the group and continues the same turn. Groups carry per-model priority, Beijing-time active windows and expiry dates; subagents inherit their parent session's group and can also pick models or bind their own; models served by dsh-our-free-model retry another account before failing over.

Registers external ACP (Agent Client Protocol) agents such as Codex, Claude Code and Gemini CLI as DSH model providers: maps each agent's thought_level options to the reasoning-effort selector, forwards images when the agent advertises promptCapabilities.image, and routes permission requests to DSH's approval dialog; ships an ACP Agents settings page that imports Zed agent_servers JSON and discovers models.

Runs a local OpenAI-compatible gateway so DSH can use the model quota of a logged-in Tencent CodeBuddy (WorkBuddy) account: one-shot installer with SHA256 verification, logon scheduled task with duplicate-launch guard, manage.ps1 for status/start/stop/restart/logs/update/uninstall, and an agent skill that drives setup and troubleshooting.

Adds a Codex sign-in page to DSH settings, driving the built-in llm-pi-ai OAuth flow for browser or device-code login and showing masked account status without a separate provider or credential store.

A Neon Genesis Evangelion-inspired skin for DeepSeek Harness: Title Card (light) and Central Dogma (dark) modes over one removable override layer, 55 measured color tokens, a wallpaper paint layer whose two surface alphas are solved against a WCAG contrast budget, a boot mask and a brand mark. It also rewrites the sidebar identity line, replaces the new-session heading, hides six official entries, and reshapes the composer control row. Unofficial fan work, non-commercial: the background pictures are fetched from third-party URLs at paint time, not shipped in the repository.

A configurable Liquid Glass theme for DeepSeek Harness with translucent surfaces, wallpaper, desktop transparency, window blur, custom cursors, click ripples, and per-side conversation contrast controls.

Cuts session input tokens three ways, each with its own switch in a panel under the composer: lossless structure-aware compression of tool results on `tools/post-execute`, then a per-tool head/tail elision that always names a recovery path through the shared spill store; tool-catalogue visibility per agent on `agent/created`; and a per-workspace memory document that recall matches against each new message and injects through `agent.inject`, so the transcript is not re-read. Measured 41.76% fewer prompt tokens over 149 recorded requests, with a bundled script that re-measures any profile.

Global and per-session prompt templates in a right-side panel — insert into the draft or send now, edit, promote session templates to global, with SQLite persistence via the built-in node:sqlite.

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.

Full-screen video boot splash — play an mp4 at startup, skip with a click, import your own clip, and non-playable codecs are transcoded to H.264 automatically.

Todo sidecar for DeepSeek Harness: turn selected text into a todo, capture todos from a conversation, review them in a left sidebar panel, get due reminders as an in-app popup or an IM bot message, and export everything to HTML, Markdown, Excel, CSV or JSON.

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable.

Hierarchical workspace tree plus browser-style session tabs for the DSH sidebar: a "/" in a workspace or session title creates a virtual folder, with sections, pinning, time buckets, drag ordering, unified 6px status dots, per-row appearance customization (colour, glow, weight, icon) and a floating full-text search over session titles and message bodies. Five settings switches restore any behaviour to the host default. Fork of KannaKuron/dsh-better-workspace.

Local music player: scans a folder for audio and video files, plays them in a Music tab with crossfade, a 10-band EQ and ReplayGain, and can write matched tags, covers and filenames back to the files with atomic replacement.

Code workbench in the right sidebar: a workspace file tree and a multi-tab Monaco editor with syntax highlighting and version-guarded saving, Tab completion from DeepSeek fill-in-the-middle, per-save checkpoints with rollback, codebase search (plus a codebase_search tool for the agent), and reference chips that insert a selection into the chat as an @path mention.

Your real Obsidian vault in the DSH right Sidebar: vault tree, full-vault search, read-view typography, wikilinks and heading anchors, properties, backlinks, highlights, in-place editing, an outline, and a right-click menu for handoff, rename and .trash.

Select text in a DSH conversation, a file preview or the terminal to quote it: the floating bar offers Comment, Add to chat and Side chat, and Alt+Q / Alt+C / Alt+B do the same three things. The quote - and its comment, kept in the same chip - is inserted as a native reference chip, and a sent quote stays one rounded capsule in the message that expands on click and can be copied. A hover card can jump back to the message a quote came from, and the right sidebar carries a quote list page that searches every quote of the session, jumps back to any of them and exports them as Markdown. Side chat writes the quote into the composer of one dsh-better-sidebar side thread per conversation without sending it, and that page can bring the thread conclusion back into the main composer or export it as a file. A sent quote can also be revised: the card puts its old comment back in the comment box, the corrected quote is sent as a new message, and the old capsule is marked as superseded (the transcript itself is append-only).

Select a term in a DeepSeek Harness conversation and press the Search button beside it to read the explanation in place: basic meaning, purpose and usage, with the token cost of that answer. The call is auxiliary — it writes nothing to the session log.

ChatGPT-desktop-style model picker whose thinking-level slider carries a particle trail, plus a visual-only fast-mode toggle and a hold-to-lock for it.

Claude Code-style workbench in DSH: workspace/session sidebar, streaming document-style transcript with unified tool cards and thinking, Markdown and Mermaid rendering, dark theme, and a draggable overlay panel backed by an in-host HTTP/WebSocket service.

Let Agents directly control independent local DSH instances with zero intrusion—no plugins or components required on the target. Isolated environments enable autonomous configuration and testing, while Agents with different models and personalities can chat, role-play, or form nested control chains. Supports conversational setup, user-like operations, incremental reading, saved references, and remote session/workspace search.

Expert roster for DeepSeek Harness: 636 experts across 22 divisions with full Chinese names and bios, summoned as subagents from the @ menu or by the model through list_t_experts / summon_t_expert / summon_t_experts, plus custom experts and a skill on/off switch.