Плагины

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.

Переиспользует встроенный режим зрения DeepSeek web для текстовых моделей: инструмент deepseek_vision управляет локальной браузерной автоматизацией deepseek-vision-cli (помощник ручного входа, включённый deep-think, автозакрытие браузера) и возвращает описания изображений текстом.

Профессиональный перевод для DSH: 18 целевых языков, 4 стиля (formal/casual/technical/literal), терминология под управлением глоссария и перевод целых файлов (README/docs/subtitles) с сохранением формата Markdown/блоков кода; работает на DeepSeek через SiliconFlow.

Двухвременная (bi-temporal) память на базе демона SodaMem: воспоминания подмешиваются в промпт при сборке каждого хода, и каждый закрытый ход загружается в память — без вызова инструмента и без вызова модели на пути чтения; каждый вспомненный факт ссылается на ход, из которого пришёл, и несёт даты действия, поэтому вытесненные факты перестают извлекаться.

Жёлтое однострочное уведомление о промахе кэша промпта после перестроения кэша; показывает повторно оплаченные входные токены без кэша, токены попаданий в кэш и TTFT.

Задачи по расписанию на основе настроек, выполняемые в заданное время или в часы низкой загрузки DeepSeek, с разовыми и ежедневными расписаниями на основе устойчивого состояния задачи.

Нативные инструменты веб-исследования Search1API (s1): поиск, новости, обход страниц, обнаружение sitemap и трендовые темы как полноценные инструменты `s1_*`, с встроенным skill s1.

Врата проверки на реальных вычислениях: упрощение математических выражений, логические доказательства, проверка regex, FOL через E-prover, проверки конечных автоматов и исправление кода на основе бинарников, скомпилированных на Go, с готовыми исполняемыми файлами для Windows.

Менеджер обновлений установленных плагинов: проверка обновлений, резервное копирование и откат.

Second-model gate on the assistant turn, installed in two parts: copy engine/ into ~/.dsh/plugins/ and mount it by absolute path in the profile patch (the bundle itself only installs the settings panel), then switch off the default dry-run mode that only logs verdicts. Once active, a separate judge call scores the draft against the numbered criteria (0-10 each); any criterion under 6 fails the turn and sends it back for a rewrite, up to 3 rounds by default. The web panel edits criteria and thresholds, and every verdict is appended to an audit log.

Task ledger: a dsh plugin that has the agent create, claim, advance and close tasks, writing each step straight into a plain-text ledger in the workspace so the owner, the current state and the next step stay on record; no cloud service is involved, single-user and multi-user both work with Git synchronisation, and a control panel summarises in-flight, overdue and stalled work with weekly trends.

Reads local AI session history from 16 AI tools plus Windows recent-file activity, and generates daily or weekly work reports on your machine. Currently Windows x64 only: the plugin ships a bundled Windows sidecar (no Python needed); macOS/Linux are not supported yet.

Adds a "Handoff session" item to the session context menu: pick an older session, choose how the new one should read it, and a fresh session is created with the handoff instruction pre-filled in its composer while the old session stays untouched. Three read modes — the AI decides what to read, a six-part summary written into a .md file, or just the last 20 turns. The second tab turns those .md files into a cleanup list grouped by workspace, deletable once the receiving session has run 3 turns or the handoff is 7 days old. All file, record and turn-count operations run in the host process; the browser half only renders and requests. Requires Windows and the DSH desktop app (it uses Electron shell.openPath and explorer.exe/cmd.exe).

Registers 12 CatPaw (妙手) models as a DeepSeek Harness provider, with per-model reasoning effort, harness-executed tool calls, and QR-code login. The bundled catpaw-cli is a macOS arm64 binary (other platforms must supply their own copy), and calls use the signed-in CatPaw account quota.

Interactive code-graph visualization inside DSH: a sidebar entry (a tab inside dsh-better-sidebar when that plugin is installed) draws the graph produced by dsh-codegraph (its .codegraph/codegraph.db or the codegraph CLI) or by dsh-tool-lens, with call-chain tracing, cycle detection, dependency and impact analysis, directory/file/function clustering, four layouts, and PNG/SVG/JSON export. Requires dsh-codegraph or dsh-tool-lens as the data source; without one the graph is empty.

Follow list above the sidebar conversation list: a status dot per conversation (unread, waiting for you, running, failed), newest reply first, running ones last, and a follow toggle beside the model selector.

App Updater for DeepSeek Harness: detect every installed app that has a newer version and update it with one click by downloading the vendor's full installer from its official website and installing it silently — without launching the app. Windows (winget

The cyber-elixir of youth for the desktop client: fixes the `desktop welcome: Web authentication failed` (HTTP 431) launch failure — an Electron random-port launch lets `dsh-auth-*` login cookies pile up per port (70+ of them, ~229 B each), the startup request headers blow past Node's default 16 KB cap, and the client can no longer launch. Two fixes in one: a scriptable cleaner that removes leftover login cookies from the cookie database (Chromium SQLite) — explicit, offline, keeps a `.bak` copy, `--expired-only` narrows the scope — and a `patch` feature on the settings panel that fixes the launch port through the profile `cordis.patch.yml`, so the client always starts from a single port and cookies stop accumulating across different ones (rewrite `port` as a `!!js` expression to keep the `--port` flag in charge; a per-profile snapshot makes one click revert it). Read the README for usage. Interface, CLI output and market metadata in 9 languages. The purge runs from the bundled CLI (`dsh-cookie-cleaner --clean`) only while the client is fully closed; the in-app half is read-only. npm: `dsh-cookie-cleaner`.

A memory plugin that forgets on purpose: short-term memories expire after 48h, long-term ones are rescheduled by Ebbinghaus/SM-2 curves and rarely-used ones fall asleep instead of bloating your context. Long-term writes stop in an approval center, so the agent cannot rewrite your persona on its own.

Local task checkpoints and bounded recovery for DSH, with optional L0–L3 hierarchical memory, dependency-aware retrieval, prerequisite-aware context, and six opt-in memory tools.

Two-stage session deletion for DSH on Windows: move a conversation to the recycle bin and restore it to its original sidebar slot; deletion confirmed in two steps to prevent deleting files by mistake, clearing the whole subagent tree, sidebar ledger, projection cache, log lines and exclusive attachments along the way. It also scans the files a conversation actually wrote, adds a file query that pastes the path information into the conversation so an agent can judge which files are safe to delete, highlights them in Explorer, and copies the paths grouped by type. Both this and iamwuzhanglin/dsh-session-recycler install under the package name dsh-session-recycler, so install only one of them.

IM stand-in seat for DeepSeek Harness: a sidebar panel polls Feishu/Lark, WeCom and DingTalk (switched on from the panel) through the platform CLI you are already logged in to, and wakes the DSH session you bound when a new message arrives, so that session reads it and replies as you — drafts are shown to you first unless you have explicitly allowed sending without confirmation. Groups are polled only after you add them to the watch list, and by default only @-mentions wake the agent; blocked chats are never fetched, message bodies stay in a local state file, and the plugin opens no port of its own.

Drives the OpenCode client already installed on your machine through its loopback opencode serve API, so its free-tier models work in DSH — the child process starts on first use, and OpenCode executes no tools of its own: a call it proposes is handed to the DSH tool of the same name and run there, or refused when there is no equivalent. No API key is needed.

Windows-only guard against the desktop shell locking itself out: it counts the dsh-auth-* launch cookies the shell has accumulated, reports how much of the 16 KiB request-header budget they consume, and once the count passes 40 it backs up the whole Cookies database and lets DSH rebuild it, so every cookie in that profile is cleared. Install is one command: on load the plugin registers its own weekly scheduled task pointing at the scripts inside the package, and uninstalling it removes that task — nothing to copy into your home directory and no schtasks line to run by hand. The check itself runs while the app is closed (it waits up to 3 hours for the shell to exit). It does not raise the header budget or keep a floating panel; scripts/ can also be run standalone without the app installed.