Plugins

Long-term memory on top of mem0 and a local Chroma store: user profile and recalled facts injected through the system prompt, capture at session end, a nightly pass that dedupes, merges paraphrases and resolves contradictions, a persistent topic graph written as Markdown cards, periodic export to a git repository, and a full-page memory UI with search, bulk merge, snapshots and undo. Needs a manual Python venv setup plus LLM and embedding API keys before use.

Progress tab for the DSH right sidebar: the turn status of the session and the progress long-running tasks reported, in one tab beside the conversation.

Adds a manual "mark as unread" action to workspace session rows, and retires itself once the harness exposes the same capability.

Collects the sessions that need you into one dock at the bottom of the web GUI sidebar: running sessions, sessions waiting on an approval, plan review or answer, and finished runs whose result has not been opened yet. Rows are sorted by last update and clicking one switches the main view to that session; it reuses the shipped useSessions and useSessionStatus hooks rather than adding a data source, polls nothing, stores nothing and modifies no session. The header dot pulses while anything is running or waiting and settles to a static dot when every row is only a finished-but-unread reminder; with no such sessions the dock collapses to one quiet line, and a collapsed 56px sidebar shows a 36px badge with the count instead of the list. It registers in the sidebar footer slot, so it is part of the layout and does not overlay the conversation list, leaving the existing footer entries below it.

Offline LAN chat inside DSH: direct chats, group chats and file transfer between machines running the harness on the same network, with UDP auto-discovery, CIDR scanning to add contacts, an optional access code (unset by default), local-only contact aliases, per-message and per-conversation deletion, and a configurable per-file limit. The host opens its own HTTP/WebSocket port for peers, and the plugin imports only node built-ins.

Adds a connection-test panel under Settings -> Models: reads the deployment's model catalog and probes each configured model with one minimal chat round-trip (a short "ping" with a small output cap) through the Host LLM service, verifying connectivity with a real request. Each row reports success/failure with the harness failure code (NO_ADAPTER, MISSING_CREDENTIAL, AUTH, RATE_LIMIT, TIMEOUT, ...) plus first-token/total latency; single-model and concurrent test-all (3) are supported. Credentials are resolved inside the Host process and never reach the browser; probes are independent per model behind a same-origin-fenced route with a body-size cap. Pure JS, no build step, MIT.

Adds Meta's Muse Code subscription as a DSH model provider: the bundle declares the shipped Meta route under Settings > Models, syncs the account chat catalog (Muse Wonder included) into the model picker, and adds a Sign in card plus the /muse-login command that run DSH's built-in Meta device-code flow, keep the minted key renewed, and show a red or green credential dot. Needs an active Muse Code subscription and no Meta CLI.

Adds a Claude Pro/Max OAuth provider with multiple accounts, optional account failover, cached quota reporting, live model catalogs, and quota UI in settings and conversations. Uses the Claude Code client identity; quota reporting uses an experimental endpoint.

Bailian (DashScope / Model Studio) model catalog in the DSH settings page: lists every model the configured API key can reach, groups them by model family, probes whether a model is actually callable (an unopened model answers 403, which DSH reports as an invalid key), refuses to add models that fail the probe, and shows the active session's context window and remaining budget. An sk- key has no balance endpoint, so quota here means context quota.

Stardew Valley theme (full-skin edition) for the dsh web UI only: replaces the served web frontend with a self-contained pixel-farm interface — Junimo dialog, farm-select presets, quest journal HUD, session-as-day valley calendar, chiptune SFX and desktop pets. Not available in the desktop window and not compatible with other UI-changing plugins.

Sidebar account-balance quick view for DeepSeek Harness: balance, bonus credit, current model and the official peak/off-peak pricing period, with ruby/amber/jade/gold tiers and a low-balance warning.

DeepSeek balance chip in the sidebar name row, showing the balance, the current peak or off-peak window, and a countdown to the next switch; click to refresh.

Per-answer timing breakdown: splits each reply into model, tool and other time, with first-token, decode and per-tool totals, and keeps a local JSONL ledger. Needs Node 24 or newer in the DSH runtime.

Per-model API price table with Peak and Off-Peak rates in USD or CNY, the DeepSeek account balance and live session spend under the composer, an all-time total, a collapsible source URL and check date per model, and optional per-model Peak schedules.

Pins your DeepSeek Harness account balance to the bottom-right corner and refreshes it every 60 seconds, with a click for an immediate lookup.

Shows the remaining DeepSeek account balance in the composer dock, right after the cache-hit reading, and links to the Platform usage page. Requires a signed-in DeepSeek account; API-key-only setups show nothing.

Quantify what switching projects costs. Measures each workspace's cold-start overhead (AGENTS.md + skill catalog + tool schemas + runtime context), its steady state, and how many turns it takes to reach it — then compares workspaces and attributes the difference. Attribution requires at least three workspaces and says so instead of inventing a correlation from two points; a factor with no spread across workspaces is reported as a property of the profile, not of the project. Recommends which workspaces to keep warm, which to archive, by entry cost times visit frequency. Deterministic.

See what a conversation actually costs: how many model requests, how big the system prompt and tool table are, cumulative tokens, estimated spend, and how far you are from automatic context compaction. Reads the local session log only; never calls a model, never adds a word to the system prompt. Token and spend figures are estimates from character counts, not provider usage.

Tree-style questioning for DSH: click "Ask in tree" on a selection to add a node to the right-sidebar tree and ask inline under it; clicking another node makes it the current parent, so later selections nest there, Alt+click opens a root node, Ctrl+click appends another passage to the same node, double-click jumps back to the quoted text, a red/green dot marks each node as understood or not, and the panel switches between a list view and a horizontal branch graph. "Add to composer" instead puts the quote into the input box as a reference chip, without creating a node. Nodes live in localStorage and nothing is injected into the prompt.

Replace the DSH solid background with a local image, with a draggable editor for fit, blur, veil and interface opacity.

Adds a time-aware greeting line under the DSH home hero headline: seven local-time slots with tsundere whale-girl lines, phrase overrides through ~/.dsh/greeting.json, and Ctrl+R / F5 bound back to a real page reload.

Shows a character avatar and an editable ID beside every assistant reply, and reads the reply aloud with the system voice or a local TTS service you point it at; includes presets, a playback bar with pause and sentence skipping, tone and speed controls, and one-click launching of that service.

Read books in the DSH sidebar - import EPUB/TXT/Markdown, get a five-part close reading for every chapter (paragraph summary, best sentences, what the author is doing, the AI's own opinion, what is missing), listen with TTS, ask questions while listening, and export the whole book to one HTML page. Export collects the chapters that already have a close reading rather than unread chapters.

Count-up Pomodoro: focus counts up with no ceiling and never stops itself at 25 minutes, finishing drops straight into a short break, and a status board plus the four quadrants keep the task list in view.