Plugins

Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.

Command Code Provider API chat for DSH with a Host-held API key, discovered model catalog, effort defaults, an optional zero-data-retention header, quota meters, and per-model OpenAI or Anthropic protocol selection.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

WeChat official account AI writing pipeline: six-step article runs (topic, outline, draft, gates, render, images) with a launch brief contract, a hot-topic board with per-item AI digests, RRULE scheduling to the draft box, a workbench UI plus chat tools and a /wewrite command, and fail-closed host approval before any draft-box push.

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in place of the access-mode selector, and permission requests, AskUserQuestion and ExitPlanMode routed to the native DSH approval, question and plan-review cards. The stream is written as native DSH session events, so the built-in transcript, tool cards and nested subagents render it; Claude slash commands merge into the command palette; the CLI is held by a detached broker, so plugin updates and DSH restarts do not interrupt a running turn.

Separate slash-command group in the Web UI composer: /steer injects text on the agent's next step without interrupting the turn, /new starts a blank session, /skill and /docs wrap /steer with post-turn skill or docs tasks, and custom /steer aliases are configurable in Settings.

Codex-style /btw command: answer side questions in a conversation-seeded subagent (fork provider), rendered in the UI without entering the main session history.

Runs 3 or 5 coding-agent candidates in detached Git worktrees, validates their patches with project commands, ranks only passing candidates, and requires separate approval before applying the winner.

Per-execution HTTP/SOCKS5 proxy routing for Agent fetches, LLM providers, and shell commands, with settings-backed hot reload, approval-gated controls, and credential-safe status.

Command history for the Web UI composer: press Up/Down to cycle through previously sent instructions, then restore the draft at the end of the history.

Unified messaging gateway for DeepSeek Harness: 27 IM platforms (Telegram, QQ, WeChat, Discord, WhatsApp, Feishu and more) in one plugin, with QR scan-to-authorize, per-platform workspaces, slash commands, and a web setup dialog.

Task-driven plugin equip engine: dual retrieval (curated rules + LLM semantic), combo scoring (synergy/conflict/cost/trust), conflict detection and install-command export.

Adds a "Work Roles" tab and a pixel-art office overlay to the DeepSeek Harness Web UI: 508 built-in role cards (The Agency 255 + agency-agents-zh 253) with search, EN/ZH toggle and department filter; draggable Canvas 2D pixel characters that stand, type and pace, with idle chat that can plug into AI. One-command npm install, no dsh source changes.

Background stream listeners that wake the DeepSeek Harness agent — put a watch on a command or file and receive new lines as in-session notices. Ships a daemon host so a watcher can run unattended for weeks.

Unified IM channel for DeepSeek Harness: Feishu, Telegram, DingTalk, Slack, Discord — persistent conversations, true streaming replies, 40 MCP Feishu tools, slash commands, and an IM-bot status tab in the plugin settings.

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.

Tested-curation lab for DSH plugins: every entry passes real install/static-scan gates in an isolated environment, with full logs and reproduction commands (Chinese-first).

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

SSH remote ops for DSH: pair servers over SSH or a one-time-code remote-hostd, then run commands, manage background jobs, and read or write remote files with reviewable changes (host_pair/host_bash/host_jobs/host_read_file/host_write_file/host_review_changes).

Ask-before-act approval for every edit and every bash command: a red/green line diff before a file is touched, a description+command panel before a command runs — approve once or reject, each gate with its own master switch in Settings → General.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.