Плагины

Проверка гигиены Git: сканирование только для чтения объединённых и устаревших веток, слишком больших отслеживаемых файлов, неотслеживаемых файлов и незакоммиченной работы с рекомендациями по очистке (ничего не удаляет).

Запускайте Stata через DeepSeek Harness: нативный сервис Stata AI Skill запускается автоматически вместе с DSH (бинарники macOS/Windows включены), так что регрессии, do-файлы и эконометрические рабочие процессы работают без ручной настройки.

Предпросмотр созданных файлов прямо в чате: при клике на чип созданного файла Markdown (server-side markdown-it + highlight.js), изображения или обычный текст рендерятся прямо в разговоре; открыть в системном приложении и показать в папке остаются в одном клике.

Вызываемый моделью инструмент `vision` для DeepSeek Harness: описывает и распознаёт текст на файлах изображений, напрямую вызывая бесплатный Zhipu GLM vision API (цепочка fallback glm-4v-flash), без внешнего CLI.

Сканер первоначальной настройки репозитория только для чтения (инструмент repo_setup_scan): определяет stack/тесты/документы/git/db и рекомендует плагины, MCP-серверы и файлы гигиены.

Веб-приложение для просмотра файлов для DSH: интерфейс React и REST API, обслуживаемые хост-веб-сервером, команда /dsh-agfs, открывающаяся в текущей рабочей области сессии, и инструмент модели browse_files.

Sticky-заметки рабочего пространства для DSH, сохраняемые как несколько Markdown-файлов в текущем рабочем пространстве.

Инкрементальное монтирование файлов с дедупликацией чтения: смонтированные диапазоны строк никогда не отправляются модели повторно, изменения на диске делают монтирование недействительным и перемонтируют его, есть вкладка Mounted Files и учёт экономии токенов.

Панель разработчика справа для DeepSeek Harness: файлы, история сессий и контроль версий git

2D engineering prints (PDF/PNG/JPG) of plate parts to noBS CAD scripts and STEP files: modelling skill, CAD tools over the noBS CAD MCP engine, packed native print probe, and a 2D → 3D panel in the Web UI.

Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH native agent teams, resolved at spawn time by wrapping SubagentRuntime.startContinuable. No official files are modified.

Drive DSH from anything that speaks HTTP: 47 routes (REST + SSE) for workspaces, sessions (create/prompt, live SSE generation, history, stats, todos, cancel, ask-user Q&A), models and the global default model, providers, agent presets, settings namespaces, skills, and workspace files including resumable chunked upload — plus an OpenAI-compatible /chat/completions, a built-in OpenAPI 3.0 spec and an interactive request page. It only injects the host webServer and tools, so it rides on the DSH webserver (default prefix /api/v1) or its own port with optional API-key auth, and it ships a skill that teaches the DSH agent to call the API.

IDE-style Git panel in the DSH Web GUI: a resident tab with a three-column overview (branch/tag list, searchable commit-history graph, commit detail with changed-file tree and message) and a changes page (stats bar, uncommitted list with per-file stage/unstage/discard, commit box with amend); side-by-side diffs carry lazy highlight.js syntax highlighting, on-demand between-hunk context expansion and word-level intra-line emphasis, with image files shown as before/after panes; plus a zsh-style branch marker in the input bar. Every git command runs as an argv array through the host subprocess service, cwd locked to the repo root.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in report files at the workspace root.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

Drag documents into the dsh web chat; the agent reads them directly from the local filesystem and the right sidebar lists the outputs and file paths.

Shared browser panel for DeepSeek Harness via Better Sidebar, with local Chromium, human and agent mouse and keyboard control, page snapshots, screenshots, and per-chat persistent profiles.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

A dsh-better-sidebar tab that statically parses Qoder Canvas `*.canvas.tsx` files into structured pages in the DSH right sidebar (the source is never executed: no eval, no bundler, no sandbox iframe), with a file-viewer takeover for `.tsx` and a bundled Skill for authoring the format.

A dsh-better-sidebar tab that renders a session brief — a todo board read from the `todos` projection plus a deliverables section listing the files written this turn — and hides the official todo panel above the composer while it is mounted.

Resolves the original local path of files uploaded to .dsh-uploads by matching file name, size, and sha256.

Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.