プラグイン

Matrix digital rain: drapes the chat window in the classic green character rain — cascading columns with incandescent white heads and green tails, streaming the tokens the agent is generating into the rain in real time; opacity, speed, density, font size and colors are all adjustable, and rain intensity follows agent activity.

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, hidden-models blacklist, live per-task cost, prices and context windows, a refresh button that re-syncs every provider model list from its live API, and the

Node.js fork of andyfan1094/dsh-winrm: the same WinRM host panel and seven agent tools, with the backend ported from Python/pywinrm to a native Node WinRM client so the machine running dsh needs no Python.

Windows desktop control connector: through 10 agent tools it captures the screen (including occluded and partially off-screen windows), lists and focuses windows, moves, clicks, drags and scrolls the mouse, and sends key chords or arbitrary Unicode text. Built on koffi FFI: no compiler, no per-call subprocess, and its own GDI screenshot plus PNG encoder.

Windows-only process control for the harness: a sidebar button that shuts DSH down through the host's own graceful exit path, an app-window / normal-tab switch on the Plugins card that rewrites the desktop shortcut and restarts, and advanced settings for the wait before exit, the process exit code and a force-quit option.

Turns the LobsterDaddy multi-account console into a floating ball in the DSH window: drag it anywhere and the position persists, and the panel can be set to follow the ball. Clicking it slides out a drawer that renders the console as native DOM (no iframe) from the loopback-only same-origin proxy, showing action buttons, the account LobsterAI is currently signed in as, and a per-account list with balance, check-in state and last check-in time; a resizable persisted drawer, a live online/offline dot and an account-count badge are included.

DSH plugin: discover this machine's HTTP proxy (proxy env vars, else the Windows system proxy) and make DSH use it — for the agent's in-process fetches and for every child process it spawns.

Fixes the Windows workspace-open action. The shipped opener runs `explorer.exe "<file:// URI>"`, which on some hosts reports success without raising a window — the exit-code verdict cannot tell an opened window from nothing happening. This routes that one action to `explorer.exe /e,<dir>`, which raises a window reliably, and leaves every other application in the menu on the shipped path.

A headless-first macOS Computer Use driver for DeepSeek Harness with AX-first observations, window-bound multimodal evidence, host-owned approval, and evidence-backed action receipts

Shows a reminder card in the bottom-right corner of the DSH web GUI whenever the agent is waiting for your answer, and adds a desktop notification plus a flashing tab title when you are on another tab or window.

Scene-awareness probe for DSH on macOS: a privacy-first, pull-model `look` tool that reads the frontmost non-self window (app info, AX title/selection, gated local OCR), plus a summon-hotkey snapshot captured the instant you press.

Windows desktop control through UI Automation: nine tools that read a window control tree and drive elements by id through their own UI Automation patterns, with every write gated by an approval policy, an append-only action log and a settings panel.

OpenCode Go provider that verifies a model against the gateway rather than treating a recommendation as a measurement: the models.dev protocol suggestion is probed before it is used, reasoning levels follow a measured contract, and requests run through an ordered protocol fallback chain. Context window, max output and image-input numbers are declared by a runtime-refreshed models.dev layer rather than probed, with operator overrides above both. Several OpenCode Go credentials can be stored and switched from the settings page.

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

Holds DeepSeek model calls for the rest of each peak-hour window you configure instead of sending them, so they are billed at off-peak rates; also pauses active goals while it waits and shows the account balance with an 8-hour spend chart.

Shows the active model's usage and remaining balance in the session header: OpenCode Go plan usage (rolling, weekly, monthly) with the selected model's monthly cap, Command Code 5-hour and weekly window usage with remaining credits, and DeepSeek account balance.

Configures from the settings window's General page whether Enter, Shift+Enter and Ctrl/Cmd+Enter send the message or insert a line break; the engine default is kept until you change it.

Speaks a short status line when DSH changes state — turn done, turn error, job done, job failed, goal complete, goal blocked, an approval waiting, or the agent needs your answer — using eight pre-recorded clips in Chinese (default) and English. The audio is played by the host process through ffplay, or through the Windows PowerShell player that ships with the OS, so it does not depend on a Web Audio tab. Windows only.

Rapid-refill circuit breaker for DeepSeek Harness automatic compaction. It refuses a compaction that would be futile — the context refilled within fewer than N tool turns M times in a row, which the unbounded step-pressure trigger cannot detect — and instead of burning a summarization call on every step it reports the situation with advice, usually that a single read or tool output was too large. Shows state and re-arms through /compaction-breaker, and injects one prompt section so the model relays it to the user. Covers host-plane sessions through its profile bundle; ordinary sessions need one row replaced inside an agent preset.

Turns the browser PWA shortcut already on your desktop into a real launcher: it adopts that shortcut and keeps its icon, then starts dsh web silently on double-click and opens the app window; adds restart and dsh self-update (with rollback) controls to the web UI. Windows only.

Desktop notifications for DeepSeek Harness — a web notification while a browser page holds the plugin (turn completion and pending questions), and a native Windows toast from the host for finished turns once the browser is closed.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.

Shows the DeepSeek account balance as a row in the sidebar footer with a refresh button, and opens a popover with the balance card, daily token and estimated-cost charts over a 7/30-day window, a per-model table, and a link to the platform usage page. The balance comes from the official /user/balance endpoint; usage is aggregated from local DSH session logs and priced with the published peak/off-peak rate card in CNY, so it is labelled an estimate and its scope is stated on the panel.

Shows token and CNY cost per turn and per session in the harness's own statistics form, a whole-account bill over 1/7/30-day windows with cost-per-unit-of-work trends, and an advisor that re-measures its own suggestions after you adopt them.