Плагины

Удаление сессий DSH из веб-интерфейса и десктопного клиента: опасная кнопка в шапке и пункт меню в строке сессии с диалогом подтверждения риска; серверный эндпоинт и инструмент агента удаляют журнал сессии, кэш проекции и учёт рабочего пространства.

Защитный guard для mcp__omni__parse в DeepSeek Harness: слушатель tools/pre-execute, который запрещает URL-адреса частных/зарезервированных хостов (SSRF), применяет allow-list или запрос (согласие) и закрывается при пустом allowedRoots.

Перемещение сессии в другую папку из веб-интерфейса перетаскиванием или через выбор в меню, безвозвратное удаление сессии с диалогом согласия на риск и переименование сессии ИИ путём суммаризации всего диалога (с учётом опечаток). Каждое действие также поставляется как инструмент агента.

Delete sessions from the DSH Web sidebar: adds a Delete action to the session row menu with a risk-consent dialog, then removes the session log, workspace accounting and live session state.

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

Task-aware DSH plugin navigator: builds a local index from GitHub topics and community lists, retrieves across 28 bilingual capability classes, and provides commit-level static risk audit, consent-gated pinned installation, composition checks, and recovery.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Figma design context for the agent: reads a frame's node tree, auto-layout, paints and typography, resolves the variables it is bound to, and renders a screenshot to compare code against — plus four bundled design-to-code skills. Connect with one button against Figma's own consent page; the plugin ships its own OAuth app, refreshes tokens automatically, and never asks for or displays a token.

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

Delete sessions of a DeepSeek Harness profile from the UI: header danger button + session-row menu item with a risk-consent dialog; host endpoint + tool delete the log, projection cache and workspace accounting. Works in web and the desktop client alike.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.