Plugins

Renders a Live2D Cubism 4 model as the DSH web UI background: a transparent click-through canvas that covers the window without blocking any control. Eyes, head and body follow the pointer; expressions track the agent state (thinking, running a tool, turn finished, error, waiting) and the conversation (message arrives, reply ends, question asked); after an idle delay the character shows speech bubbles and plays motions and expressions drawn at random from pools you tick. Settings list the models under ~/.dsh/live2d-stage/models, expose position, scale, opacity, gaze strength and every interval and probability, and open a resizable live preview of the same canvas. Expressions and motions a model3.json omits are detected from the model folder; one sample model is included.

Floating photo companion for the DSH Web UI with a 15/25/45/60-minute focus timer, water and stretch reminders, Open-Meteo weather, and a session radar listing running, ended, input-waiting and permission-requesting conversations for one-click navigation.

Windows desktop only (Windows 10/11, DSH desktop 0.2.1-rc.5 or newer; not available in `dsh web`). Open any DSH conversation in its own native window, so several conversations can be shown at once.

Conversation-branch canvas: full-bleed session lineage graph, fork from any message, parallel runs with live streaming, deterministic branch comparison, and a per-session agent swarm web view.

Managing chat conversations in DeepSeek Harness

Off-peak task queue: typing /闲时任务 in a conversation queues a task with no model call at queue time, and DSH runs it in that same conversation during the off-peak hours of the model that conversation uses (DeepSeek off-peak half price, GLM Coding Plan half credits).

Show workflow stages and subagents on a timeline, configure model and concurrency for each stage, and reopen subagent conversations from the panel. Run names and stage settings persist under ~/.dsh.

Save conversations and manage Markdown notes in DSH or a separate window, with search, history, templates and private GitHub sync. Verified on Windows only; sync needs your own GitHub account (Git or the GitHub CLI).

Background browser automation for DSH: one Electron host gives each conversation its own window, with shared login state, CDP input, snapshot refs and no focus stealing.

Gives one conversation a pinned as-of point and a dated evidence window on both sides — \[as_of − before, as_of + after], past, future or BC. In restricted mode the agent is told the active window once per change, web_search results are filtered to dated sources inside the window and undated sources are rejected, and the first reply must echo the window (a missing echo gets one nudge). It also narrates long silent background jobs with deterministic \[TIME FACT] facts and exposes a read-only time_pin_status tool; default mode injects nothing and filters nothing.

Delegates independent tasks from DeepSeek Harness to the local OpenAI Codex CLI and returns the result to the current conversation. Provides four tools (task execution, status check, danger-mode toggle, enable/disable switch), enforces a real-path working-directory whitelist with symlink-escape protection, defaults to Codex workspace-write sandbox mode, passes the task body as a single argv argument to avoid shell injection, kills the whole Codex process group on timeout or cancel, and caps output length. Requires Node.js >= 20 and a Codex CLI build supporting codex exec.

Recycle bin for conversations - delete a session from the sidebar into a trash folder, undo within 8 seconds, restore or delete forever later.

Adds an incognito toggle for in-memory DSH conversations with temporary desktop attachment storage.

Inventory of the MCP servers, skills and hooks a DSH profile has, plus a conversation tab reporting every tool, skill and MCP server a session actually called.

Floating card above the composer with the conversation's spend, the account balance and the current peak/off-peak billing period, plus a per-answer cost figure under every finished turn.

Lets the conversation AI maintain a plain-language functional requirements checklist in a dedicated session view. A non-official rebuild of Songran241/dsh-req-workbench that keeps the upstream package name; do not install it alongside the upstream original.

A left-sidebar gallery of every file the assistant wrote, edited or delivered across all conversations, grouped by file type with preview thumbnails and one-click open. Document previews and the open / open-with / Trash actions require macOS; the gallery, text previews and filters work anywhere.

Native UI cards instead of Markdown: the assistant calls render_ui and the answer renders as a card in the conversation — 29 block types (metrics, tables, charts, timelines, kanban, flow charts, clickable actions), a content auto-layout mode, four placements (inline, process, dock board above the composer, turn-tail next-step card), a schema-backed settings form, and an optional automatic next-step card. Cards are rebuilt from the recorded tool arguments, so they survive replay and fork; 253 offline tests, no build step.

Bundle for the sessiongraph capability — install this package to add local conversation-history search to a DeepSeek Harness profile

Pairs a phone console with the current DSH Desktop conversation. Running /phone shows a one-time QR code; after pairing the phone can send messages, approve tool calls, switch models and stop the task, while the desktop stays the only execution host. Requires AgentBridge running locally.

Pick a Git branch, or name a new one, on the New Session screen and start the conversation inside an automatically created worktree, so the current checkout stays untouched.

Project workspaces for multi-session collaboration, conversation handoffs, searchable chat records, and editable shared memory; automatic memory curation and handoff judgment require two background models (memoryModel and sessionManagerModel) configured in the plugin config.

Restarts the DSH desktop host on macOS when a change needs it, then hands the conversation back to the same session with a note the model writes about why it restarted and what comes next.

Browse and continue DeepSeek web conversations in DSH, or import them with attachments into a workspace.