Plugins

A Multitask agent preset where the main conversation only plans, briefs subagents and summarizes results, while file reads, commands, search and builds run inside subagent contexts; four worker kinds, an approval gate for dangerous operations, and zero changes to DSH source.

Proxies the loopback-only dsh web onto a LAN port so phones and other machines can reach it, with an optional access password that browsers type in and the bundled Android client unlocks with biometrics. Adds a LAN-access settings page with QR codes, inlines dsh-web-mobile (MIT, attribution kept) for the mobile layout, and the Android client in the same repository adds finish/approval notifications, voice input and a home-screen widget.

Remote DeepSeek Harness with full server-side API access (`settings.*` / `credentials.*` / `host.listDirectory`). Token-gated reverse proxy, per-device sessions, phone invite QR, fence self-check, optional approval / CIDR / idle timeout / local TLS, WebSocket/SSE.

Long-context preparation, Dream memory, task verification, workflows and computer interaction for DSH. Needs DSH 0.2.2-rc.2 and Node.js 24.9+. The default install configuration grants full file and command access and turns execution approval off; explicit settings in an existing profile take precedence.

Run Claude Code, Kimi CLI, Codex CLI, PI CLI, OMP CLI, OpenCode and CodeBuddy CLI (off by default, unverified) inside DeepSeek Harness sessions over ACP, with a CLI and model menu, a git changes panel and worktrees in the Web and Desktop UI. Needs each CLI installed and signed in (OMP, OpenCode and CodeBuddy must be installed first). The CLI runs outside the DSH sandbox and decides what to ask: only Claude Code in manual mode and OpenCode with ask permissions raise DSH approval cards, Codex, PI and OMP run commands without asking.

IMAP/SMTP email tools (list/read/search/send/folders/attachment/health/watch/mark/reply) with since/until date-range filters, email_mark for read/unread/star/move, email_reply for reply/reply-all/forward with threading headers, QQ/163/126/Sina/Aliyun/Gmail/Outlook/iCloud presets, multi-account support, a send-approval gate, a web settings page and a whale-girl new-mail popup driven by the incremental email_watch checker. Outlook OAuth2 device-code login works out of the box through a built-in community client, and an account can still supply its own clientId instead. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Computer use for Windows: screenshot, mouse, keyboard, clipboard and window tools with per-app access that goes through DSH approval; while the agent is in control the screen shows an orange glow and a status bar, and Esc pauses or resumes.

Cursor-style IDE mode for DeepSeek Harness: one click on a workspace menu turns the main panel into a VS Code-like workbench with a Monaco editor, file tree, Git panel (commit graph, push/pull, per-file revert), SSH hosts and a real PTY terminal on the left, while the official DSH conversation stays docked on the right so tool calls, file edits, approvals and session history keep working as you code. Built on a craft-first belief: write it by hand, understand every change, treat AI as an assistant and stay the first owner of your software.

Deep PTC mode is an open-source agent preset for DeepSeek Harness that keeps the built-in PTC tool surface and replaces the persona with a working contract: a DeepSeek identity and unlimited-token-budget instruction so the model does not skip reads, commands or checks to save tokens; planning by estimated size (internal up to 5 minutes, shown without approval up to 20, approval required beyond); and asking about unclear intent instead of guessing. Waiting is limited in code by wrapping the official shell, job and question tools: foreground commands move to background jobs after 30 s (configurable), a steered user message ends the current wait so the model reads it, foreground pauses over 5 s and long timers in run_code are refused, and questions run in timed mode. The mode derives its preset from the official PTC declaration shipped by the installed Harness and inherits upstream composition changes, so an official PTC update — including removed or renamed modules — does not break existing sessions. A settings card selects the preset executor — Automatic, WSL Bash, Windows PowerShell, native Zsh or native Bash.

Runs your logged-in Claude Code CLI as a dsh model provider: live model list, session resume, approval relay, rewind, memory panel and remote SSH workspaces.

Feishu (Lark) UI for DeepSeek Harness — a panel-driven control console: every slash command is a button on the ⚙️ control-panel card, in-card approvals and questions, live streaming cards, and one-QR app setup.

QQ official bot channel for DeepSeek Harness (feature-rich fork of tencent-connect/dsh-qqbot): group and private chat with the full agent, sticker library with auto-tagging and AI meme replies, group management (join approval and mute), botplay interactive card events with paginated catalogs, user extension registry (custom slash commands and QQ tools), scheduled wakeups, remote approvals over QQ, and a floating dock web UI.

QA project workbench for dsh: manage test projects, requirements, test cases, defects, milestones, reports and approval gates through a browser UI and 18 QA-domain tools.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Live2D desk pet overlay for the DSH web GUI: mirrors agent state (thinking, idle, error, done, awaiting approval) with motions and speech bubbles, per-part touch reactions, drag-to-dock, switchable personas, and custom models via URL or local path.

Task-event notification center: 6 event kinds (ask / approval / completion / subagent completion / error / turn end), dual channels (browser Notification + host system toast) plus Bark/Webhook push channels (ntfy, Gotify, self-hosted gateways); quiet hours with urgent exceptions, approval-timeout re-reminders, completion-storm aggregation, and notification text redaction.

Four-source migration wizard: move Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DSH (/move wizard with approval gate and idempotent move.json, resumable sessions).

Official-grade GitHub CI integration: a composite action.yml, a polling PR review bot with idempotent inline comments and a status-check gate, plus PR/issues tools with every write gated by human approval.

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

A visual workbench for reference-image generation, cropping and component-wise Tripo 3D modeling, with per-task paid-operation approval and local asset previews.

Two-way iMessage channel for DeepSeek Harness over Photon: sender allowlisting, session commands, in-chat approvals and questions, and a Settings page for device authorization and hosted-line setup.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

ROS2 debugging toolset and robot-state vision analysis for DeepSeek Harness: node/topic/service/action/interface/TF enumeration, whole-graph topology JSON, rosdep checks, approval-gated builds and custom message scaffolding, GUI screenshots and multimodal vision observation, plus headless RViz2 offscreen rendering (low-poly meshes, direct pixel read, GPU passthrough - motion rendering at 30Hz) with parallel VLM realtime analysis.

Windows desktop computer-use tools (click, type, key, screenshot) with freshness checks, approval gating, process-identity verification around every action, and a sanitized audit trail.