Plugins

Embeds a real VSCode editor (code-server, or your local desktop VS Code via the bundled bridge extension) as a GUI tab: agent file edits open turn-scoped red/green diffs that survive tab closes and page reloads, files lock while the agent writes, and a watchdog supervisor keeps zero orphan processes.

Enterprise AI resource platform as a 22-plugin cordis bundle: org/account/role IAM, OIDC provider and App SSO, MCP server management with the platform itself exposed as an MCP server, NAS asset storage, skill hub, agent and app registries, SaaS connector management, enterprise portal data channel, department agent workbench panel, DingTalk group bridging for message and approval push, one-click remote dsh enrollment with tool proxying, usage metering, wallet billing, model gateway, audit with alerts, self-update, and a reviewed third-party plugin marketplace — 70+ ops tools become callable by the dsh agent.

Task panel for the DSH Web sidebar: publish tasks, auto-distill related sessions, and drive plan/develop/review stages with subagents plus in-panel acceptance.

AI Company Framework: turn one sentence into a multi-agent company — 15 flat Skills (boss/pipeline/role-template/11 roles/generic customer-memory), 7 workflow templates, AgentTeams runtime + activity panel, employee sidebar with per-session isolation, Feishu bot bridge (boss and per-employee bots, group routing, autonomous push, human decision gate, external-contact guide), per-customer SQLite memory with three-layer memory (cross-group merge), /company mode switch; no RAG.

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.

Header quota badge plus a usage-monitoring tab: live balance/quota remaining and reset countdown per provider, with requests, tokens (input/output/cache-read/cache-write), cache hit rate, estimated cost and average latency tracked per session, provider, model and client, stored locally in SQLite with cross-device import/export.

Peer-to-peer colleague-agent consultation for DSH: ask one or several configured peers, queue asynchronous questions, discover peers through signed friend cards, and review inbound requests in the Web UI.

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.

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

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.

Displays the images read in the conversation (read_image results) in the DSH Web GUI: a Read image row with a default-expanded message-style image card over a PS-style transparency checkerboard, merged read-N-images rows with side-by-side frames for multi-image requests, and an in-page full-resolution lightbox (zoom buttons, mouse wheel, 1:1 original size).

Voice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).

Fetches any http/https page and returns title, description, main text, heading outline and links, with stats (char/word counts, reading time, language) and top keywords; can download content images to the session workspace for vision analysis and dispatch them to registered analyzers via the scrape.imageAnalyzer service.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation, with automatic formula health checks after every edit.

⭐ Drag-and-drop uploads of any file or whole folders, anywhere in the window; remote-safe — bytes go straight into the session workspace on the server, so a DSH deployed on a remote machine works exactly like localhost.

Curated research plugin market: adds a Research plugins page to Settings with hand-reviewed plugins for literature search, reference management, writing and workbenches — one-click install, update and remove pinned to the reviewed version, restart from the panel, and exactly one network request (its own catalog).

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Turns coding into an RPG: finished turns, tool calls and completed todos earn XP, with 27+ achievement badges, levels, titles and seasons. Event-driven scoring with a pure-function engine — the work itself is the game.

Edit the host-wide global instructions (~/.dsh/AGENTS.md) from a dedicated Customize page in Settings - every session on this machine applies them.

A starter template for dsh plugins covering config, tools, events, services, hooks, browser UI slots, and slash commands.

Journals every AI file write/edit into before/after snapshots for an inline VS Code review flow (accept/reject hunks, per-file undo, no git).

GitHub search, discovery and audit scripts wrapped as a SKILL.md pack around the gh CLI: repo search, multi-axis explore, trending, repo summaries, similar projects, code search, issue/PR search and org audits; ships as a dsh bundle (and on npm).