Plugins

Use a PackyCode (PackyAPI) API key in DeepSeek Harness through a built-in multi-protocol model route with key rotation and balance display

Adds three settings pages to DeepSeek Harness: add, edit, enable and remove MCP servers; write agent skills by hand or install them from a GitHub repository; and keep a library of global personas with one active.

Three-tier deny/ask/auto gate for the computer-use (cua-driver) tool family: each tool category gets one segmented control in Settings, and an allow list or deny list overrides the tiers per tool name.

Multi-cluster Kubernetes management panel powered by local kubectl, with resource filtering, YAML editing, live Pod logs, interactive container terminals, workload restart/scaling, and DSH theme synchronization; accessible from the sidebar or session view. Requires DSH 0.2.0-rc.2.

Synchronizes DeepSeek Harness third-party plugin lists through S3-compatible storage with diff preview, local snapshots, rollback, and optional LLM provider configuration sync.

Reads the session event stream, with no extra model calls, and turns corrections, failures and fixes into pending lesson candidates. Every candidate is judged against written criteria and carries the reason it passed or was refused; only confirmation writes a skill, and only through the single validated writer `learn_skill_manage`. An idle curator marks unused skills stale and archives them by moving rather than deleting, and spares any skill that is still being loaded. Five tools: `learn`, `learn_review`, `learn_curator`, `learn_skill_manage`, `learn_skills`. Registers a prompt section stating the criteria, and a tool guard that refuses direct edits to skill files so the writer cannot be bypassed.

Bridges DSH to a local MemVault store: core memory blocks injected into the system prompt, finished turns extracted through MemVault's own pipeline, and a panel to browse, trace, review and replay what was stored.

Reasoning-effort gear presets for third-party models: 16 vendor/model presets with per-mode custom wire values, written into dsh-llm-pi-ai with pre-write validation and per-rule rejection; per-model switching between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages with automatic route regrouping; plus a composer Optimize button and a settings section that rewrite the input text with a model you pick.

Let a DSH model inspect and operate Windows applications through an installed Codex Computer Use runtime, with per-session app approval.

Fetch academic papers by DOI or keyword: Crossref and OpenAlex search, batch PDF download through eight Sci-Hub mirrors with an Unpaywall open-access fallback, PDF magic-byte validation, bounded concurrency, and a clickable batch-access HTML manifest for papers that could not be downloaded.

Wraps the Scrapling Python library in up to nineteen model tools, registered by probed capability: real-browser rendering for JavaScript-only pages, CSS/XPath extraction that returns data instead of Markdown, self-healing selectors, reusable login-state sessions, XHR capture, page screenshots, gated browser actions and a domain-scoped crawler with content/sitemap/feed/Shopify modes on the official job backend. It can also replace the built-in web_fetch / web_search, and serve the same tool table over MCP. Requires Python 3.14+ with Scrapling installed; the browser tools also need a Chromium engine for patchright, which an optional CLI installs on macOS arm64 only.

Turns a ZSpace (极空间) NAS into native agent tools: list, stat, search, read, download, upload, write, create folders, rename, move, copy and delete files on the NAS. Works across networks through the desktop client relay — no LAN, no WebDAV, no SSH — and switches to the faster direct WebDAV transport automatically when the NAS is on the same network. Deletes require an explicit confirm: true; write, upload, create-folder, rename, move and copy run directly, and zspace_write overwrites a same-named file unless overwrite is false.

Three-window workbench for dsh web: chat, construct, and a read-only review window side by side for each workspace, per-window hooks, and an anonymous multi-model review that asks before it runs, groups findings by issue, and reports in Markdown.

Pops the DSH side chat into a frameless, always-on-top Windows desktop window that can sit over any other application, with its own settings page for appearance, pinning, remembered geometry, opacity, ephemeral threads and cache cleanup.

Per-project MCP servers: a project declares servers in its own documents (`.dsh/mcp.json` by default; the local and global file lists are settings), and they are mounted only for the sessions working in that project — on the first turn of a session, released when it goes idle. A right-sidebar tab and a Settings page list each project with a live session, the status of every server and the session holding each mount, with `Sync` / `Retry` / `Release`, an `enabled` switch and an editor over one existing entry; a per-project tool policy (`disclosure` / `direct` / `off`) with pins and `mcp_search_tools` decides what the model sees; `${VAR}` references resolve through the project `.env` files and the credentials file; per-server call counters outlive the sessions that produced them.

DeepSeek Harness plugin: stacks the sidebar footer slot entries vertically, unifies their card chrome, and lets you drag them to reorder.

只填 Key 的服务商预设：50 家渠道为 DSH 一键写入官方 llm-pi-ai 路由与凭据（插件），并可写入腾讯 WorkBuddy、OpenCode（Key 走其 auth.json）与 cc-switch 的配置（CLI）；核心为纯 JS，可被更多应用的外壳复用。

One private Feishu group per DSH workspace with real-time two-way message synchronization.

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

Drives a Chromium browser you are already running — Chrome, Edge, Brave, Vivaldi, Opera, Chromium, Arc or Thorium — over one long-lived CDP connection, so the remote-debugging approval is asked once instead of per command. Commands for tabs, navigation, JS evaluation, DOM snapshots, clicks, typing, screenshots and CSS/DOM/pixel assertions go over a loopback HTTP route that the agent calls with the shell tool it already has, so no new tools are registered, and the plugin registers its own usage skill with no runtime dependencies.

Ranks workspaces holding a session that wants attention to the top of the sidebar session list - waiting on you first, then running, then finished-but-unopened, then just read - and draws those rows with a state bar, tinted surface and coloured title, plus a one-shot settle pulse when a run stops. Every colour is taken from the active theme's own tokens, and the three windows that decide how long a finished session stays promoted are settings.

Replaces the web profile's pwsh shell executor with a subclass that rewrites every command through `rtk rewrite` before execution for token savings, running the original command unchanged on any rewrite failure (no equivalent, missing rtk, timeout) and keeping sandbox semantics intact.