Plugins

A web Settings "Loop engine" switch that swaps the agent loop driving every dsh session among five engines — the built-in in-process loop plus hosted Claude Code, Codex, Pi, and Kimi Code — with zero changes to the harness; each hosted engine keeps its thinking and tool calls in the durable session transcript, takes over commands, skills, and the agent preset, and runs sandboxed through the dsh subprocess seam.

Adds a draggable, position-persisted chip bar of configurable quick phrases to DeepSeek Harness, plus a /-triggered phrase menu with per-phrase pin, slash-menu, bar-visibility, and click-to-send toggles.

Right-hand widget rail for DeepSeek Harness Web UI: live session stats, task/context/heatmap/quote widgets, OpenCode Go quota, multi-column grid layouts (1/2/4 columns) with 2x4 long tiles, a continuous magnification wave, and per-instance sizing; widgets are installable, reorderable and resizable from Settings > Components.

Manage Git-backed DSH plugin markets, installed agent skills and optional Codex hooks from the web settings page.

DSH plugin bridging agents to Cheat Engine for dynamic memory debugging: scanning, pointer analysis, breakpoints, and game memory hacking.

Windows-only Computer Use plugin for DeepSeek Harness with UIA, cua-driver, and optional GLM vision.

Piano-key style in-conversation navigation bar: one key per user message, hover preview tooltip, click-to-jump across full history. Official dual-face dsh plugin, no dsh source changes.

Archived-conversation manager for DeepSeek Harness: view archived conversations grouped by workspace, restore them, and reveal their transcript folders.

Migrate Codex (OpenAI Codex CLI / Desktop) MCP servers, skills, instructions, memory and session history into DeepSeek Harness with a visual panel or CLI, with dry-run previews and secrets migrated as-is.

Renders Wallpaper Engine scene wallpapers in real time in the browser (three.js player plus a Rust/WASM CPU particle simulation) and plays video and web wallpapers, falling back to the preview image, with no Wallpaper Engine runtime required. Scans the local Steam workshop library (431960) by auto-detection or a manual path, and offers a settings panel for wallpaper selection, library and engine directories, glow, pause and quality.

Windows system-tray launcher for dsh web: console-free background start (VBS/powershell chain), a tray menu with open UI / logs / icon presets / launch-at-login / restart Harness, one-click install and update of the bundled dsh-plugin-usage-meter, and a dsh plugin half that starts the tray together with the harness.

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Mobile remote suite: Host pairing plugin with QR offer, loopback Host Gateway, encrypted Tunnel and same-LAN WebRTC Direct, plus an Android APK in this repo.

Connects your GitHub account to DSH agents from the composer GitHub button (OAuth device flow or personal access token) and lets them call the GitHub API through the github_api tool.

Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.

Config-driven lifecycle hooks, including context injection: declare event, handler and outcome in YAML, where the handler is an in-harness tool (MCP included), a shell command or an HTTP endpoint, and the outcome is model-visible context, a denied tool call, or fire-and-forget.

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

Points web_search at a self-hosted SearXNG instance instead of the native route: pages until maxResults is satisfied, and reports degraded coverage when engines fail so a thin result set is not read as a thin web.

A guarded local fetch provider for the ctx.web seam — the backend dsh does not ship for its own web_fetch tool. Every redirect hop is re-resolved and checked against the non-routable ranges, with a streamed size cap and a content-type allowlist.

Progressive tool disclosure: a deferred tool group costs one catalog line instead of its full schemas until the model loads it with tool_search, with one switch per group in Settings and each group measured against the live registry.

An Obsidian-style knowledge base: ingest sources, let the LLM build and maintain an interlinked wiki, and ask questions grounded in it.

A thinking level stored per provider and model, so reasoning effort outlives the session it was set in and also reaches subagents, which dsh never asks. The in-session picker still wins, and a model with no row keeps its provider default.

Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.

After each completed agent turn, a bounded auxiliary LLM call writes one suggested next prompt into the session log; the web composer renders it as ghost placeholder text, adopted via Tab.