Plugins

Curadoria da saída de ferramentas no momento da ingestão: mantém linhas de erro e aviso mais o início e o fim, despeja o texto completo em disco com um ponteiro que o modelo pode reler; cobre todas as ferramentas de texto, e resultados pequenos passam intactos.

Tradução profissional para DSH: 18 idiomas de destino, 4 estilos (formal/casual/técnico/literal), terminologia controlada por glossário e tradução de arquivos inteiros (README/docs/legendas) com preservação de formato de Markdown/blocos de código; impulsionada por DeepSeek via SiliconFlow.

Passe o mouse sobre fórmulas LaTeX na Web UI do DeepSeek Harness para copiar o código-fonte TeX ou exportar a fórmula como um SVG independente

Operações de dispositivo e bancada ADB para o DSH: descoberta de dispositivos, logcat estruturado (streaming em segundo plano), instalação de apk, pull/push de arquivos e snapshots de desempenho via dumpsys

Integração de IA do Xcode para o DSH: 26 ferramentas MCP do Xcode (mcpbridge) + skills da plataforma Apple + persona no estilo Xcode Intelligence (preset de agente ou pacote global)

Governs the persistent information and project constraints an agent works with - project orientation and scope, information and document lifecycle, and persistent workspace mutation - through one additive system-prompt section plus deterministic runtime checks.

Account-level DeepSeek platform usage inside the DSH settings page — 52-week token heatmap, per-API-key and per-model breakdown, live balance.

Renders LaTeX in the chat — formulas inside your own message bubble, plus a live preview of the composer draft while you type.

AI-agent-driven automated testing platform for DeepSeek Harness (dsh): Markdown case library, bug reports, per-project serial queue, development board and built-in load testing.

LaTeX snippet expansion in the DSH web composer: Tab expands a short trigger into a formula template and drops the caret into the first hole, then walks the rest.

Browser automation for DSH: the agent fills in forms, scrapes lists and works across tabs in real pages, using the logins you already have. It drives its own visible window on your desktop — minimise it and it keeps working without stealing focus — and a sign-in, CAPTCHA or native dialog stops the run and hands the page back to you: it never confirms on your behalf. Login state persists (own profile plus session-cookie re-injection). 23 Playwright tools (20 always on, 3 gated and off by default), with a URL allowlist, dialog suspension and a CDP method allowlist that are mechanism-level and pinned by tests.

Windows host performance from WSL: CPU, memory, disk and top processes.

Windows desktop automation for dsh: 14 tools that enumerate apps and windows, capture window screenshots that still work when the window is covered by other windows, read the accessibility tree, and perform real input — click, type text (CJK included), press key combinations, scroll and drag. Loads the official computer-use runtime (@oai/sky) already installed on the machine, discovering it by enumerating vendor directories, so vendor upgrades that change hash directories do not break it.

Pops the DSH side chat into a frameless, always-on-top Windows desktop window that can sit over any other application, with its own settings page for appearance, pinning, remembered geometry, opacity, ephemeral threads and cache cleanup.

Session cost in rubles in the composer dock — the tariff in effect with its countdown, the API cost at that tariff, the CBR rate, the total including subagents, cache savings, and DeepSeek Platform balances.

Guards session logs from malformed model tool calls (empty id/name, non-string arguments) so a bad call can never make a session unloadable.

Usage dashboard: offline-scans session logs to chart daily/weekly/monthly tokens, estimated costs, model/tool/skill/command leaderboards, output speed, working hours and quality metrics; gridstack+ECharts cards are drag-and-drop composable, with custom formulas and AI arrangement (prompt round-trip import).

Web search provider with switchable engines, several usable without an API key (Bing, DuckDuckGo, SearXNG and others) and a fallback order between them; adds multi_search, platform_search, image_search with an in-chat image wall, page_images and save_images, plus a settings page for engines, keys and per-engine proxy.

Russian interface translation for DeepSeek Harness (DSH): registers complete ru dictionaries for the DSH platform and its plugins, adds Russian to the language picker, and activates it on first run. Translation only - no typography, spell-check or layout-

Long-term memory for DeepSeek Harness in Claude Code's format: private, overlay, or shared with Claude Code, with provenance on every file

Terraform/OpenTofu plan summary + state list (never apply).

Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.

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.

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.