Plugins

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

Bridge dsh session status to the cc-pet desktop pet bubble: thinking, tool calls, and completion in real time.

Chat with, monitor, and approve your DSH agents from WeChat via the iLink gateway: text both ways, session targeting, digest heartbeats, and numbered approval prompts.

Bridge to the Telegram Bot API: long polling, per-chat sessions, HTML formatting.

Copy and open `dsh://` session deep links, or paste them into another conversation to inject a bounded, read-only snapshot of the referenced session.

Long-term memory written by the character itself. A sorting plugin watches the workspace and, once conversations have been quiet past a threshold, opens its own session to run the bundled extraction script and turn the recent exchanges into memory files; a heartbeat plugin later re-opens sessions on a probability curve that rises with the time since the last exchange, with quiet hours and a random delay. Ships the memory templates, the sorting guide and the extraction script. Needs Python 3.8+ with zstandard, plus manual setup after install (a preset with agent-instructions, templates copied into the workspace, defaultPreset/sortPreset set to real preset ids; a wrong id fails silently with one log line). Plugin-opened sessions run with full permissions by default. Tested on DSH 0.2.0-rc.2.

An edited fork of dsh-chat-editor from WZZNNE/DSH-CyberWorkStation (MIT), with -plus ids so it can be installed alongside the original. Rewrite or delete messages the model reads — text, reasoning blocks and tool results — without replacing the message on the session surface, and branch a session from any turn.

Run JSON workflows with /workflow, inspect progress, select Agent models, resume saved sessions, and run bounded review and repair loops.

Reverse-engineering agent preset. Mounts REA (rea-agents) as MCP tools for native binaries, JavaScript/Electron apps, managed assemblies, archives and installers — the full 170-tool catalog by default — but only inside sessions that select the preset; other presets load nothing. Ships an install-time check that reports which native analysis engine (Hopper, Ghidra, IDA) is present and prints the env snippet to wire one in. A fork of dsh-rea (JeremyWangCY, MIT) retargeted as an agent preset; do not install it together with dsh-rea.

DSH-SOLO desktop plugin for its companion app. Pair by QR code to view sessions, send tasks, switch models, transfer attachments and approve operations with end-to-end encryption; official cloud relay preconfigured, no server setup required. Download the App APK at https://github.com/wudidiandian/dsh-solo/releases/latest/download/dsh-solo.apk (GitHub Releases).

Rewrites the reasoning row: instead of the raw chain of thought it shows first-person working notes, written segment by segment while the reasoning streams in, with a toggle back to the original. Notes are stored per session so history rows keep them after a reload, the note writer runs on a configured provider or a downloadable local llama.cpp model, and the model still reads the full reasoning.

Exposes a running DeepSeek Harness as an MCP server over Streamable HTTP or a bundled stdio bridge, so an external agent can create workspaces and sessions, prompt, fork, rename and switch the model on them, read and write files, run foreground and background shell commands, call the instance's own agent tools by name, and read per-turn and cumulative token usage with a cost receipt when a price plugin is installed.

Telegram sessions, topics, model controls and approvals for DeepSeek Harness.

In the DSH desktop file preview, click an HTML element (with its source line and column) or lasso part of an image for the vision model to identify, then send your change request to the current session; local HTML edits keep a history with before/after previews, line diffs and rollback.

Re-speaks each assistant report in a chosen persona outside the working prompt, with four built-in presets, per-session switches, and the original available on demand.

Publishes the running DSH host as a Model Context Protocol endpoint, so other harnesses such as Claude Code, Cursor, Codex or another DSH can start and continue sessions, read transcripts, wait on or cancel turns, and answer pending approvals; every call is attributed to its caller, and owner-scoped sessions keep callers apart.

Find keywords in the current conversation or across every session, with highlight and jump.

Drive a dsh agent from Telegram: one chat topic per project directory, voice and photo input, ordered per-topic job queue, per-topic goals and task checklists, session forks and branches, live progress message, command menu in en/ru/zh, and control commands for models, plugins, sessions and logs. Search the plugin registry, read a package card before installing, and update every plugin with one tap. Requires a Telegram bot token and your numeric user id in allowedUserIds.

Drive SoundCraft from the agent: load a session, set track and mixer levels, insert plugins, edit MIDI, and bounce audio without opening a window. Exposes the DAW's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Luna preset for DeepSeek Harness — a little-demon persona on the full standard tool set, composed by six deterministic rule layers (perception, understanding, state, style, regulation, memory) plus a derived vitals layer, with a gated, suppressible cross-session memory file.

Windows desktop control through UI Automation, window screenshots and mouse/keyboard input, with per-session app consent and action approvals.

Floating glass status bar for DSH on Windows 11 x64: an always-on-top capsule that mirrors session progress, the current step and pending approvals from a local DSH web profile, with peek and detail views; approval cards stay read-only until DSH returns its own decision receipt, and connecting to the official Desktop app is experimental and unverified.

Deep-reading workflow for books: import EPUB/Markdown/TXT/PDF into chapters, read one chapter per subagent so the source text never enters the main session, keep \[n]-anchored chapter memories for cross-session continuation, and export notes or an EPUB.

Switches the running session's persona and speaking style in place, via the composer's persona button or `/role`; each persona can bind its own on-screen mascot, the persona is appended as its own prompt section after the deployment persona without touching tools or skills, and each switch is announced in the transcript.