플러그인

DeepSeek Harness용 크로스플랫폼 Computer Use: 가상 마우스를 통한 인간 유사 조작(screen_observe + computer_click + type + key + scroll + drag, 총 11개 도구), 시각 비용 없는 AX 트리 모드와 무료 GLM-4V-Flash 비전 폴백, 안전 장치(스냅샷 TTL/앱 화이트리스트/위험 작업 승인/비밀번호 입력란 보호).

UIA, cua-driver, 선택적 GLM 비전을 사용하는 DeepSeek Harness용 Windows 전용 Computer Use 플러그인입니다.

DeepSeek Harness용 Windows 데스크톱 자동화: 접근성 우선 observe/act 루프와 표준 도구 30개(요소/좌표 타깃, auto/a11y/event 전략 라우팅), 대체된 관찰 및 재실행 금지 안전 시맨틱, 영구 킬 스위치, RuntimeId/rect-drift 스테일 보호, 채팅 카드와 플로팅 패널(라이브 ops, 프레임 월, 환경 자동 감지 설정), 저해상도 모델용 타일 비전 설명, JSONL 감사 추적, pid 허용 목록. Windows 10+ 및 uiautomation과 pillow가 포함된 Python 3.9+ 필요(설정 페이지에서 설치 가능).

Three-tier deny/ask/auto gate for the computer-use (cua-driver) tool family: each tool category gets one segmented control in Settings, and an allow list or deny list overrides the tiers per tool name.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Drive the desktop and Chrome from DeepSeek Harness using the computer-use runtime inside the ChatGPT desktop application.

macOS computer-use tools backed by a plugin-owned Cua Driver runtime.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.