Plugins

Thinking in Chinese: injects a system prompt so thoughts and replies stay in Chinese, expands the reasoning block by default with interactive collapse, and localizes UI labels (npm: `dsh-think-zh-expand`).

Phone-first mobile UI rework plus a pairing-code gateway: use DSH from anywhere as an installable PWA with Web Push, behind your own reverse proxy or Cloudflare Tunnel.

Per-plugin usage budgets and cost caps on the llm/stream waterfall: per-model usage accounting, session and monthly budgets with warn/block transitions, latency windows, and a carbon-footprint estimate.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Discovers installed DSH plugins with tags, overlap and compatibility detection, one-click enable/disable, failure diagnosis, and update checking.

Reproducible science workbench: agent-driven cells, inline figures with feedback/rerun, manifest provenance, environment snapshots, and publication-grade figure skills (9 bio_* tools + workbench UI).

ACP bridge between BitFun and DSH.

Embeds Copree (formerly AIsChat) into the DSH web UI as a native sidebar board. Copree is an open-source framework for AI group chat and programmable worlds: the AIs are residents, not tools — each has its own memory, state and personality, they talk to each other on their own, and you can watch or join in. Group World goes further: every group chat can bind a living world (its own web page + world AI + code + clock) that the world AI builds and edits through DSH workspace tools. This plugin ships the native sidebar board (contacts, pinned DMs and groups), real-time chat over a same-origin HTTP/WS proxy, Markdown/LaTeX rendering, group invites and image messages, immersive full-frame pages, and one-click mirroring of your worlds into DSH workspaces (folder + DSH session + world_* tools). Front end only: it proxies to a Copree backend you run yourself (default 127.0.0.1:5228, same repository).

Adds a multi-user settings panel to the DSH web client: usage-mode selection, member management with online status and device binding, and switching or sharing of per-member memory and knowledge bases.

Scheduled tasks: run a prompt on cron schedules, each run opens a new agent session to do the work, with workspace binding, manual run, session auto-naming, and a fullscreen task management page.

Exports the agent loop to GreptimeDB as OpenTelemetry traces, metrics and logs, with seven Grafana dashboards covering token usage, cost, session outcomes and per-turn latency.

Cross-session memory with zero-token deterministic recall (bigram-Jaccard fused with FTS5 BM25 via RRF, Chinese-aware tokenization), reinforcement that strengthens repeated observations, and procedures crystallized into SKILL.md files refined in place through an active-stale-archived lifecycle with reversible archive and rollback. Ingest and disposal each expose a user-chosen autonomy tier; conflicts and high-importance writes always go to human review, and nothing is ever auto-deleted. Requires Node 22.5+.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Mobile remote-control suite: bundle plugin with native sidebar entry and admin drawer, self-healing bearer-token gateway over LAN/Tailscale, Android app (sessions/approvals/questions/goals), /fs/* file transfer (Range resume, 2GB upload), latency-based multi-server auto-switch, offline chat cache.

Delete sessions with a 5-second undo and a recycle bin, plus an archive view to browse and unarchive, for the DSH Web GUI. Ships on npm as `@wsxwj123/dsh-session-manager`.

Usage and cost statistics with peak/off-peak pricing after the 2026-08-17 rate change, a floating summary panel, per-session breakdowns, and a day/week/month/year/all usage heatmap.

Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.

Mobile layout fixes for the Web UI on narrow screens: full-screen settings panel, one-row plugin nav, full-screen sidebar, centered popups, icon-only session-log button.

Manage MCP servers, skills, and tools for your agent — true in-context state (loaded/truncated/evicted) and per-session switches.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Offline-first UI/UX design intelligence library for DeepSeek Harness: design_recommend, design_review and design_search tools with a built-in database of 84 design styles, 192 color palettes, 74 font pairings, 99 UX guidelines, 25 chart types and 22 tech stacks, Chinese-first with zero runtime dependencies.

A-share stock analysis and screening skill: real-time quotes, technical timing scores, buy/sell signals and a managed watchlist.

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Automatically and intelligently routes each delegated task to the best configured model using aliases, capability tags, and usage guidance—keeping routine work fast and affordable while sending complex work to stronger specialists. Configure your model team in the Web UI or guided setup, run specialists in parallel with reliable result joining, and see the chosen model at a glance in subagent views and inline in Better Sidebar's Tasks tree.