Плагины

First-paint splash for DSH: pushes a branded splash page into the boot HTML as an index-injection row, so the desktop window opens already showing the splash instead of a white/loading flash. Fades out and hands over once the startup-animation plugin starts (checked via `window.__DSH_STARTUP_RUNNING__`), with a 6-second fallback (configurable via `maxMs`) so it can never trap the app behind the splash. A normal dsh.bundle plugin: no host changes, no app.asar patching.

Counts the assistant rounds that call tools without writing anything to the user, then inserts a short progress reminder as a visible user message at the next model-request boundary, so a long silent tool loop reports what it has done before continuing. A Settings page adjusts the silence threshold (default 10), the reminder wording, the language (en / zh-CN / zh-TW), whether the reminder repeats every further threshold of silent rounds, whether subagent sessions are counted, and whether Agent Teams nudges the lead only or every member.

桌宠陪看：定时截屏，让视觉模型点评你正在看的画面，投喂给 dsh-pet 的气泡。Pet watch-along for DSH: screen sampling + a vision model + dsh-pet's bubble.

Connect multiple OpenAI-compatible providers to DeepSeek Harness: discover their models, pick the ones to expose, and generate images and videos with them from a DSH session.

VT UI/UX Enhancer: reversible UI/UX refinements for DeepSeek Harness — palette, elevation, control shapes and motion shipped as patches over DSH's own tokens, slots and styles. Disabling the plugin restores the shipped interface exactly.

Adds a collapsible, draggable minesweeper board to the conversation area, with adjustable rows, columns and mine count, and a first click that never lands on a mine.

A draggable square-cake mascot that runs while a turn is in progress, sleeps when it finishes, and gets angry on errors.

Plugin steward for DeepSeek-Harness: checks every installed plugin for newer versions and installs them, snapshots the profile first and rolls back automatically when the post-update health check regresses. Also scans plugin code for risky behaviour before you install (eval, reverse shell, credential access), browses the 8.5k-plugin catalog with compatibility badges, restarts the host by itself after install/uninstall/disable, and shows everything in plain language.

LAN access portal for DeepSeek Harness with dual-password authentication and subpath reverse proxy support. Derived from wenbin-wb/dsh-bridge v2.17.8 (MIT, several modules reused verbatim); both default to port 3082, so change one port before running both. Authentication is opt-in: set the visitor and admin passwords and enable it before exposing the port to the LAN.

Privacy guard for git workflows: before git commit, git push or gh repo sync it scans the content that would enter git (local paths, user info, API keys, private keys, connection strings) and blocks anything not approved in the DSH approval UI; approved items go into a manageable, masked whitelist. Native DSH Config schema with live settings, first-push full-repository scan, fail-closed checks, zero npm runtime dependencies.

Project control plane with durable tickets, replaceable DSH sessions, a project matrix, and bidirectional UI navigation.

Skill for building a game design brief into a playable, publishable TapTap Maker project: it picks the browser workspace or local MCP route, extracts the five elements of the brief, writes a first-round prompt for a minimal core loop, iterates in the official order, checks preview and release materials, and keeps credit, credential and irreversible-action limits in view. Includes eight reference notes on the product, credits, themes and asset limits, the leaderboard, brief parsing, iteration, publishing and safety, four templates, and three read-only Python checks for brief completeness, project layout and release materials.

Makes identifiers inside inline code in chat clickable; resolves a definition, then a wrapper, then the next occurrence, and opens the file at that line in the sidebar preview.

Bundles the PrismSearch MCP server and its agent skill. Web search over Bing and Baidu with no account or API key, plus Google and Brave when API keys are set and DuckDuckGo, Sogou, 360 and Yandex when enabled in config; automatic engine fallback and an aggregate mode. Also image search, WeChat Official Account article search, and fetch_page, which returns web pages and PDFs as Markdown in segments.

Localizes the prompts DeepSeek Harness sends to the model — system prompt sections, runtime context, tool descriptions and parameter docs — into Simplified Chinese. Its Cordis API dictionary is derived from zjl1989-li/dsh-harness-zh-cn (MIT), which translates the same prompt layers at runtime; do not enable both at once.

Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.

Hippocampus: renders workspace files, DSH memories and past sessions as a rotatable neuron graph in the sidebar, with Chinese-friendly labels and automatic re-indexing on every start.

Cross-session long-term memory backed by Supermemory: pre-step semantic and chunk recall with per-session deduplication, debounced transcript upload, background LLM fact extraction (add/update/delete) with bigram and semantic deduplication, memory_search / memory_save / memory_forget tools, global or per-workspace container scoping, and a Plugins page UI for API key storage, memory CRUD, recall preview and activity log. Requires a Supermemory API key (a free monthly quota is available), and conversation excerpts are uploaded to Supermemory's cloud.

Cross-session messaging across one or all workspaces: session_list finds top-level sessions by recency or title, session_send_message steers or queues attributed messages (cold-resuming stored sessions when needed), session_create opens titled top-level sessions with an initial task, and a client renderer displays relayed messages as user-side chat bubbles naming the sender session.

Durable session handoff for DeepSeek Harness: pressure-aware handoff docs, a searchable transcript, and automatic continuation in a fresh Session. The status pip beside the input box shades from green to blue to amber to red as pressure rises.

Lists resumable Codex chats under the DSH composer, grouped by the concrete project each one belongs to, and inserts a mechanically extracted recovery context into the draft without sending it. Project ownership is resolved from the Codex project registry with path-boundary matching and labelled by how reliable it is: recorded session ownership, registered directory, unreadable metadata, or a directory registered under several projects (left unknown rather than guessed). Also reports when the stored autosave is behind the log tail, which usually means the turn ended without a stop. The chat list requires python3 >=3.8 on PATH; Windows is not supported yet, and without python3 the list stays silently empty.

Persona, mood, long-term memory and per-person ledgers for a DSH agent, with a portable soul pack for moving between machines.

Adds a relay_check tool that runs relaycheck against an LLM API relay to detect model swaps, misreported usage, truncated context and injected prompts; keys are read from environment variables.

An Auto toggle next to the model selector that schedules reasoning_effort per request: complexity is scored by a MiniMax/OpenAI-compatible model with a zero-dependency heuristic fallback (fallbacks not cached), effort ladders adapt to each model real effort list (low/high/max, low/high/highx/max/ultra, ...), heavy tool calls upgrade the tier within the same session, the lit button and reply badges show the effort actually used, and every decision plus observed token usage lands in a JSONL ledger. A standalone-button fork of imkingjh999/dsh-adaptive-effort; do not install it and the original in the same profile.