Плагины

AI-нативный плагин музыкального плеера для DeepSeek Harness: объединяет поиск NetEase Cloud Music, QQ Music и KuGou с переключением воспроизведения между провайдерами, отображает караоке-текст слово за словом с живой синхронизацией по USB HID на колонки HALO PIXELBAR и предоставляет поиск, воспроизведение, очередь, будильник и управление колонками как инструменты модели.

Видеолента в стиле TikTok в плавающей боковой панели: листайте локальные папки или SMB-NAS либо вставляйте URL онлайн-видео (yt-dlp, bilibili/YouTube, состояние входа cookies.txt); окно автоматически подстраивается под соотношение сторон видео, поддерживает полноэкранный режим, перетаскивание и изменение размера, Range-стриминг и endpoint очереди видео агента.

Проактивное ограничение частоты запросов по провайдерам на основе token bucket: ставит превышающие лимит запросы в очередь до отправки, предотвращая ошибки upstream 429.

Межсессионная очередь задач с заметками передачи: сессии и субагенты добавляют, забирают, завершают и отменяют задачи в общей очереди на основе файлов, оставляя сводку передачи для следующего исполнителя.

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.

Team knowledge base for offline knowledge sharing (FDE box scenario): browse, full-text search and refinement entry points; raw material is queued automatically and distilled into wiki pages by a serial bot session (Karpathy LLM Wiki pattern: immutable raw, two-step refinement, log stream, monthly lint).

DeepSeek Harness peak-hour message queue: defer selected sends and deliver them to the original conversation off-peak. / DSH 高峰消息暂存与低谷自动投递。

WeChat login watchdog for DSH: surfaces dsh-wechat session loss as a Web UI banner instead of silently dropping queued messages. AI-generated, educational use only.

Manageable one-tap text chips above the session composer; idle sessions queue the message and running sessions steer at the next safe boundary without rewriting the draft.

Split-screen workspace for the DeepSeek Harness web GUI - chat with several agents side by side in panes that look and behave exactly like the stock conversation: drag-to-split, live sessions with queued messages and in-pane ask_user/approval cards, per-pane view tabs (Chat/Trajectory/plugin views), a compact TUI composer mode (Alt+T) and pane-focus shortcuts. Requires DSH 0.1.5+.

Background notification plugin: desktop notification, with a tab-title fallback, when an approval prompt or an ask-user-question card appears while the page is in a background tab. The host queues approval and question events behind a same-origin endpoint that the client polls every 3 seconds; clicking the notification focuses the page, and the tab title is restored once the page becomes visible.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Security-focused Feishu (Lark) channel for DeepSeek Harness: allowlisted remote-agent access with workspace-scoped paths, symlink checks, risk-based approvals, session isolation, redacted logs, and bounded message queues.

Guardian state engine for the DeepSeek Harness — assertion counting, edit review queue, and no-feedback-loop monitoring over session events

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

Reorder the messages queued while a DSH agent is busy, from inside the official queue dock: a drag handle and per-row ↑ / ↓ buttons on the dock's own rows, applied on the host as one concurrency-checked inbox splice. The dock is decorated rather than replaced, so previews, inline editing, steering, removal and attachments stay as shipped. A move is refused when the queue has changed since the caller last saw it, when the row is not a user prompt (a goal round prompt, for example), or when the queue belongs to a subagent session.

Genshin Nicole PV wallpaper skin for the DSH web GUI — 14 subtitle-free frames rotate on a timed crossfade queue with pause and manual switching.

EN: Selectable neo-brutalist/pop-art themes for DeepSeek Harness Web with calm reading surfaces. 0.5.10 fixes the queued-message banner and the composer attachment button in every variant. ZH: 面向 DeepSeek Harness Web、兼顾安静阅读表面的新粗野主义与波普艺术主题。0.5.10 修复全部变体的排队

EN: Usability-first cyber-editorial themes for DeepSeek Harness Web with reversible lifecycle effects. 0.4.5 restyles the composer attachment button and the queued-message dock. ZH: 面向 DeepSeek Harness Web、重视可用性并支持可逆生命周期效果的赛博编辑主题。0.4.5 适配输入框附件按钮与排队消息面板。

Pressing Enter with an empty composer steers the first queued message into the running turn while the agent is busy.

LeisureTimeQueue is a local leisure-time task queue plugin for DeepSeek Harness.

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

Adds a sidebar music browser with multiple public sources, persistent background playback, queue advancement, and reviewed MusicFree-compatible source extensions.