Plugins

Shows chat images as a thumbnail grid inside the message body instead of one collapsed icon, so several pictures are readable at a glance, with the column count adjustable from 1 to 12 (3 by default) and a hide-images switch. Clicking a thumbnail opens a lightbox that zooms by wheel or buttons, drags to pan, pages between images and downloads the original. Adapts DSH kernel 0.2.2-rc.1.

Layered long-term memory MCP server: raw turns → task fragments → daily summaries → topic indexes, local MiniLM 384-dim embeddings or OpenAI-compatible API backend, semantic + Jaccard-fallback search, one-command DSH plugin install.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

Pixel-art reasoning-effort slider for DSH Web with continuous 0–100 dragging, 16ms throttled writes, snap-to-level commits, and a WebGL ember fire that ignites as the slider moves.

Life-story skill: capture moments and fragments, build a user profile and generate novels, scripts or autobiographies.

TikTok-style video feed in a floating sidebar window: swipe local or SMB-NAS folders, or paste online video URLs (yt-dlp, bilibili/YouTube, cookies.txt login state); the window auto-fits the video aspect ratio, with fullscreen, drag-resize, Range streaming and an agent video-queue endpoint.

Extends the DSH web chat drag-and-drop to accept every file type: non-image files are saved into the active session workspace so the agent can read and use them.

A floating cyber wooden fish widget — tap it to strike and accumulate merit, drag it anywhere on the page.

One-click create, update or remove the DeepSeek Harness desktop shortcut with switchable custom icons and a draggable whale button.

Session-scoped @file/@folder mentions in the composer with Git-aware indexing, drag-drop and paste managed uploads, and validated path markers.

Move a session to another workspace by dragging it onto the target workspace header in the sidebar: the session is cloned with full history into the target workspace and the original is archived.

OpenAI-compatible image generation in DSH Desktop chat: generate inline, edit reference images or chain-edit previous results directly (image-to-image) without re-uploading, with storage cleanup.

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON unit, approval-gated writes with `(sessionId, seq)` citations, deterministic recall plus session-query FTS over past sessions — no external server, no custom SQLite.

Download progress panel: URL downloader, agent shell/SSH transfer tracking and workspace black-box file-growth monitoring, shown in a draggable floating panel with live bytes, speed, percentage and ETA.

dsh-skin 增强版：为 DeepSeek Harness 提供皮肤切换与自定义背景壁纸。在原版基础上修复了两处问题——① 大图/特殊格式上传无响应（改用 createImageBitmap 直接解码、增加处理中与错误提示）；② 主题切换时 overrideTokens 触发 theme/change 导致无限递归栈溢出（加皮肤/明暗守卫断开循环）。壁纸存储从 localStorage 压缩方案改为 IndexedDB 原文件直存，全画质显示、零压缩，并自动迁移旧数据。

Persistent multi-session split view in the DSH main window — open one or more sessions side by side in resizable panes with grid, shelf and column layouts, drag-to-reorder panes, and a sidebar entry to reopen the booth.

Code can Vibe, progress must be Visible. No guess, less stress. See progress you can assess. Make project progress visible with local algorithms, optional AI assistance, task checklists, and subagent tracking. View overall progress, subagent activity, current operations, and estimated time remaining in a draggable panel. Supports DeepSeek Harness Web and Desktop. Requires Harness ≥0.2.2-rc.1 and Node.js ≥24.9.0. Local estimates require no additional model requests. AI assistance is off by default; enabling it incurs charges from the selected model provider. Probe usage and estimated costs are available in the panel.

Draggable music ball for the DSH Web UI with a local library, album covers, playlist, favorites, collections, cover zoom, auto-hide, and source-aware deletion.

Sidebar registry for SSH servers, expiry dates and service URLs, with Windows DPAPI-encrypted password and private-key storage, explicit host-key verification, login tests, and agent SSH execution that asks per command by default or can follow the session permission.

A patch set for DeepSeek Harness that repairs fused tool-call argument text at the llm/stream seam and re-throws whatever it cannot prove: a call is dispatched only when every fragment parses to a plain object, the first call keeps its id and synthesized ones are marked, and a stream that cannot be split keeps its original error instead of a success. It also listens on agent/request-error to name the deterministic refusals it will not retry, answers per failure class which patch covers it and whether that patch is switched on in the profile you point it at, and reads multi-frame zstd session logs offline to count every turn ending and every error code. Everything it claims is registered with the seam it touches and the limits it does not cross; the resolver never invents a value and never downgrades a configured setting.

Tag manager for DSH: create, search and delete tags, with soft-delete and per-item mappings used by the workbench task, site and storage plugins.

Storage records for DSH: names, brands, locations, units, stock text and tags with local SQLite and optional metadata sync.

Configurable context compaction with three independently switchable sections — whole-context checkpoint, reasoning compression and tool-output pruning — each with its own pressure threshold and method. Mechanical modes make no model calls; model modes summarize fragments in batches with a configurable provider and prompt. A left-sidebar panel exposes switches, method cards and editable parameters that save without a restart, and every rewrite is archived with its original text.

Local long-term memory for DSH: extracts preferences and project facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts. Requires Node 24+; the offline self-evolution loop needs an OpenAI-compatible LLM endpoint and API key.