Плагины

Полноценная рабочая панель сбоку: рендеринг и редактирование файлов, терминал, Git и субагенты; сторонние плагины могут регистрировать новые вкладки.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Плагин агента для workflow-инжиниринга harness/loop, управляемый навыками (skills).

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

Автоматическая дистилляция диалога: фоновая рефлексия субагента + создание/обновление skills.

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Live subagent run monitor for the Web UI: a sidebar footer trigger plus a fixed top-right card panel showing each subagent of the current session in real time (running/elapsed, terminal outcomes, tree indent), with one-click jump into the child conversation and a return button, refresh-surviving and mobile-hidden by default.

Непрерывная самоэволюция: версионируемое, проверяемое и безопасно откатываемое состояние harness (промпты, память, skills, спецификации субагентов), совершенствуемое по траекториям сессий, с контрольными точками ревью и горячей перезагрузкой skills.

Стратегии повтора и фолбэка LLM на основе ролей.

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Migrate and import a whole Claude Code or Codex setup into DSH. Skills, slash commands, MCP servers, hooks, subagents and permission rules, with a dry-run moving estimate, a migration diff report and a post-move doctor; installs as a plugin exposing a movein_from_claude_code tool so the agent can do the move for you.

Session change-review plugin for DeepSeek Harness: tracks write/edit tool calls per session and renders line-level diffs with customizable colors, with session isolation, subagent aggregation, and SSE live updates.

Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.

Настраиваемая система профилей субагентов: единый инструмент subagent + параметр profile, с настройками в Web UI, прогрессом в реальном времени и деревом субагентов.

Expert-mode agent preset for DeepSeek Harness (v0.3.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. Features: Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), expert persistence, cross-expert communication protocol, cross review, and experience pool. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

Интерактивные фоновые агенты для длительных сессий в DeepSeek Harness: запускайте устойчивого возобновляемого дочернего агента из любой сессии, следите за его прогрессом в сайдбаре веб-интерфейса, пишите ему в любой момент и прерывайте его — всё через официальный интерфейс субагентов.

Отображает субагентов и запуски устойчивых рабочих процессов сессии в виде живого DAG со статусом, навигацией и историей, устойчивой к перезапуску.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Per-subagent LLM provider/model selection with role templates.