Plugins

Renderizador de diagramas Mermaid para a conversa da interface web: transforma blocos de código mermaid em cartões interativos (zoom, ajuste à largura, visualizador em tela cheia, alternância prévia/código) com primitivas oficiais da interface, e mantém o bloco de código original com um aviso de erro embutido quando a renderização falha.

Um porte enxuto do Headroom: comprime a saída de ferramentas e corta até 20% do contexto, sem afetar o cache de contexto do modelo nem o desempenho do agente.

Descobre e verifica papéis portáveis do RoleHub, fixa cada pacote exato e então lança seu prompt e suas skills empacotadas numa sessão DSH isolada e continuável, com vinculações de ferramentas aprovadas pelo Host e anexo opcional ao Agent Team Room.

Passe o contexto focado adiante sem esperar ou interromper o Agent ativo: congele um snapshot limitado da Session, resuma-o assincronamente com um LLM isolado sem tools e entregue uma cápsula com proveniência a outra Session ou Room autorizado — silencioso por padrão para Sessions, com wakeup explícito disponível.

Connect DeepSeek Harness to shared AgentsChat rooms over MCP and WebSocket wake bridge for cross-agent messaging, peer code review, proposals, voting, and OKRs.

Windows commit-charge watchdog for DSH Desktop: samples committed memory every 5 seconds, attributes it to the DSH process tree and the largest consumers, blocks automatic restart when DSH is not the main committer, and adds read-only pagefile advice, a 7-day crash timeline and an event export; automatic restart and crash resume are both off by default.

Production pack for ComfyUI inside DeepSeek Harness: submit API-format workflows to a local or remote server, batch-generate and fetch outputs, and diagnose bad images with measured parameter ranges and a failure-mode decision tree (black frames, duplicated subjects, color fringes, OOM).

Mermaid diagrams for DeepSeek Harness: on-demand rendering, theme-aware, with a fullscreen zoom viewer.

Whole-interface zoom for the DSH Web UI from 70% to 160%, driven by Ctrl+wheel, DSH's shortcut center or an inline pill, with content-width compensation so zooming out fits more text instead of narrowing the column.

Restores the DSH right sidebar divider drag after whole-interface zoom shifts the host handle off it, and widens the hit area to 12px with a hover affordance.

Phone pairing plugin for the DeepSeek Harness desktop — scan a QR to enroll your phone over a code-derived TLS-PSK channel. Clean-room design, zero runtime dependencies.

Agent Community UI — Bot list, room list, chat panel, run status

Meeting notes for dsh: one meeting per conversation, transcribed and speaker-separated on the machine itself, with points, assignments, handwritten notes, reviews and monthly scores in the same panel. Exports SRT/Markdown/Word and packs a meeting into a portable zip another dsh can import; confirmed assignments go to DingTalk/WeCom in one click, following your robot settings. Recognition models are swappable (a stronger local model can be imported from a file), and cloud recognition is off by default with no request made before consent. Word export needs Python and python-docx; the first run downloads a recognition model (28 or 77 MB).

Runs the upstream Headroom compression toolkit (headroom-ai, Apache-2.0) inside DeepSeek Harness over MCP: headroom_compress, headroom_retrieve and headroom_stats are exposed as mcp__headroom__* tools backed by the upstream server, installed on demand by uvx. Compression is lossy but reversible — originals are fetched back by hash from a local CCR store. Also ships a registrar that adds DeepSeek Harness to Headroom's own MCP registry, and a model-header sanitizer for the upstream proxy.

Chat wallpaper: use a local image, a local video or one of six preset gradients as the chat background, with clarity, opacity, zoom, position, dark veil, fit mode, motion and glass panels; files stay in IndexedDB and nothing is uploaded.

Ctrl+wheel page zoom (60–180%, remembered) for the whole DSH UI, plus a bottom-right Settings entry that opens the host settings panel, with Ctrl+0 to reset.

In-chat image viewer for the web UI: takes over content image clicks (Markdown images, message attachments rendered as blob: URLs, and read_image results) and opens a dialog with pointer-centered wheel zoom and an editable percentage, drag pan, 90° rotation, download with progress, copy as PNG, open with the default app, and ←/→ gallery browsing across the conversation.

Renders the open conversation's Mermaid diagrams as a right-sidebar page, one card per diagram, each clickable to open full screen with zoom and pan; the chat's own code block is left untouched, so copying or quoting the source still works.

Hold Ctrl and roll the mouse wheel to zoom the whole Harness Web UI around the pointer, 50-200% in 10% steps; Ctrl +/- and Ctrl 0 from the keyboard; a bottom-right chip and a Page zoom row in Settings → General show and reset the level.

Available on npm as dsh-doudizhu-lan. Three-player LAN Dou Dizhu (斗地主) played from a floating window: one machine opens a room on its own port, the other two join with a six-character room code plus an address. Empty seats can be filled by computer players in four switchable strengths (easy, medium, hard, hell), so one or two people can still play a whole hand; the deal starts as soon as the three seats are filled. 54 cards in four suits, bidding of 1/2/3 or pass, the landlord takes the three bottom cards and holds 20, play runs clockwise, and the first-bid seat rotates clockwise between hands. The rule engine is pure and covers 11 legal shapes, with big joker > small joker > 2 > A > K down to 3, suits never compared, straights, pair-straights and planes excluding the 2s and the jokers, and a rocket that beats everything. The table itself is built to be read at a glance: three seat cards side by side in play order (you, then your next and previous seats) with role, hand count and a bar that runs out, one line that says whose hand is on the table and what would beat it, the bottom cards as text, an in-place play history that folds into a single summary line and unfolds into every trick including the passes, plus hint and auto-play buttons that pick the cheapest legal answer out of the local rule enumeration. Nicknames can be changed mid-hand (twelve characters, duplicates get a suffix). Computers run inside the authority and are handed only their own hand, the public record and the seat counts, so no hand can leak; the authority is the only place that decides which card ids leave it. Computers are driven by the room itself, so a one-person table keeps playing with nobody else on the LAN port. Humans have no turn timer, the collapsed floating pill can be dragged around the screen, and 179 unit tests pin the rules, the wire format, the theme tokens, the drag gesture, the history grouping and the computer seats.

Persistent Bots and group rooms inside DSH — each Bot keeps its own model, permission preset, workspace and session across restarts, and every answer is a run written to a ledger the sidebar panel replays.

Adds a right-column panel that compares a set of images the user picks from the workspace — 1/2/3/4/6 per page, per-image zoom and pan, the zoom and viewed position of one image synced onto the whole set, and a reorderable filmstrip. The browser loads every image, so none of it reaches the model.

Session map: a fork-tree canvas over DSH sessions, and a Settings page that clones a Git repository into a new workspace. The canvas is reachable from a session-header toggle and two right-side tabs, and from a conversation tab that is off by default; it starts on the current session's own tree, growing downward, with wheel pan, Ctrl/⌘-wheel zoom, a subagent-session filter and a per-session overview of turns, steps, model time, tool time, output tokens and running state. The clone page takes a repository address and a remembered parent directory with a native folder picker, offers a per-clone shallow switch (off by default), runs git clone on the host, and registers the cloned directory as a workspace.

Zoom only DSH chat messages and input (80%–200%) using Ctrl shortcuts or settings, with local memory and no sidebar scaling.