Plugins

Exits the dsh CLI process automatically when the Web UI closes, with a configurable grace period and dry-run mode.

Exposes dsh's internal capabilities (language, workspace registry, agent-status and approval events) over HTTP under /dsh-api on the local loopback socket dsh already listens on, with SSE fan-out at /dsh-api/events.

Checks git commit messages against the 7DGroup convention (Chinese type tags, length and punctuation rules) before committing, as a client-side guard before GitLab pre-receive hooks.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

DeepSeek Harness memory and knowledge hub that routes update, retrieve, and subscribe calls across compatible plugins, with an optional transactional Rust backend.

Recover deleted or corrupted dsh sessions (session.jsonl.zstd) and memory (memory.db) from the raw disk, and repair rebuilt sessions that fail to resume via the /session-repair command in the web UI.

Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.

Rotates the model status line through a 53-phrase English/Chinese deep-theme pool: a random pick at turn start, event-driven switching on new thinking segments or tool calls (3s throttle), and a click on the status line toggles the language.

Desktop profile for dsh: native Tauri window over the harness web surface with tray, native notifications, a file-manager panel, and one-click updates.

Select text in a finished assistant reply to add numbered comments beside the quote; collect drafts and submit the batch through the official composer as one user message.

Conversation outline for DeepSeek Harness: the Markdown headings of the whole session, grouped by turn, in a side panel or a full-width curtain; hover previews can be pinned for comparison, bookmarks keep the places you come back to, and a right-click jumps to a section or copies a heading and the levels below it. Six theme colours and a translucent material, title/prompt/full-text/cross-session search, reading-position follow and a Chinese/English interface.

Message timeline rail for DeepSeek Harness web chat: evenly spaced ticks for each user message on the right edge, click to jump, hover to preview.

Composer GitHub picker: click the GitHub icon at the bottom-right of the input box to search the workspace repository's issues and pull requests via the gh CLI, and insert the reference as a URL or @owner/repo#number mention.

Add six languages (繁體中文, 日本語, 한국어, Français, Deutsch, Español) to the DeepSeek Harness Web UI language options, with hand-polished per-language translations and automatic fallbacks (Simplified-to-Traditional conversion for zh-TW, English for the others) covering upstream updates and third-party plugins.

Transactional data-only configuration pack manager with integrity, ownership, preview, diff, and rollback safeguards.

Draggable whale companion with local progression, achievements, skins, and privacy-safe activity tracking.

WeChat iLink ClawBot bridge: official Tencent iLink protocol, Web UI settings (QR login / model / preset / permissions / session management with delete), 24h auto-renewal pushes a fresh QR before expiry, zero downtime.

Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

A 轨迹解读 (trajectory interpretation) tab that summarizes each user round — what was wanted, how the assistant thought and executed, files/commands/errors — via a rules engine plus optional LLM narrative; user messages stay verbatim.

Codex-style token usage panel: whole-instance cumulative/per-session peak tokens, longest chat & streak, daily/weekly/cumulative activity heatmap, and plugin/skill Top5.

Design Studio tab: design briefs become html/css/js mockups with live preview, element picker, design-agent chat with vision review, identity presets and zip export.

Read-only Claude Code compatibility bridge for DeepSeek Harness: Skills, Rules, command Hooks, and Agents from .claude as SSOT.