Плагины

Windows UI Automation from WSL: enumerate top-level windows, read a bounded element tree, and wait for or trace the path to a named element.

Read Windows service state from WSL: list services, or inspect one by name with its dependencies, logon account and binary path.

Read-only Windows registry access from WSL, restricted to an allowlist of key prefixes; list a key's values or its child keys.

Read recent Windows event log entries from WSL, filtered by log name, level, provider and time window.

Windows security posture from WSL: Defender real-time state and signature age, recent detections, exclusions, and firewall profiles.

Windows desktop automation for dsh: 14 tools that enumerate apps and windows, capture window screenshots that still work when the window is covered by other windows, read the accessibility tree, and perform real input — click, type text (CJK included), press key combinations, scroll and drag. Loads the official computer-use runtime (@oai/sky) already installed on the machine, discovering it by enumerating vendor directories, so vendor upgrades that change hash directories do not break it.

Unofficial Zhipu Qingyan (chatglm.cn) web provider — run DeepSeek Harness on web-app credits with a login token, streaming and prompt-bridged tool calls included.

An enhanced fork of dsh-any-background. Its own work, from v0.4.0 onward, adds a dual-lane wallpaper: the same picture down each side of the window, split at the exact centre so the wallpaper stays visible beside the conversation column. Each lane can also read its own folder (one directory per side) while sharing a single rotation cadence and mode, and both lanes take identical edge feathering.

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.

DSH plugin: only ping me when the agent has really finished AND I have not come back for N minutes. Configurable dwell, brief result summary, plain SMTP or a local outbox.

Replaces the sidebar workspace region with a two-tab browser: several workspace roots stay registered side by side while conversations are filed under the real working directory of each session, with a read-only resource tree that previews files in the right sidebar. Hiding is per tab, display-only and fully reversible; a resource folder or file can be copied as a path or dragged into the composer as a native reference, and @ completion covers every registered root rather than the working directory alone.

Local images and videos as the DSH desktop window background: timed rotation with 0.7s cross-fades, first-frame-ready before fading in, automatic light/dark ink for readability, adjustable blur and panel/sidebar opacity, video thumbnails, and a probe endpoint reporting load, layer and selector health. Reads only the local files you point it at.

Honest merge of two community plugins into one calmer display: the streaming reading view from dsh-better-display (fork) and the message rail from dsh-tidychat. For theme lovers it wraps reasoning prose and tool-call output in translucent message bubbles, so text no longer sits directly on busy wallpapers or skins where it is hard to read. Cross-version rc adaptation attempted across DSH 0.1.0-0.2.0 (all rc); no obvious problems so far.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Renders assistant replies with numbered citation chips and a sources panel for web-search results, inline pictures with their source captions, and KaTeX formulas, Mermaid diagrams and highlighted code in streaming Markdown.

Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co

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

Windows desktop control exposed as native DSH tools - whole-screen and single-window capture (the window one goes through PrintWindow, so a covered window still captures), click, drag, typing, keyboard shortcuts, scrolling, window management, pixel and window polling, and UIA queries that can invoke a control or read its value instead of clicking coordinates. 13 tools over a PowerShell 7 child process; no MCP server, no resident process, no API key.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

A planner board as a third tab beside chat and trajectory: a Monday-first month calendar above per-day cards holding title, note, times, three importance levels and a completion checkbox. Plans repeat daily, weekly or on weekdays with an optional end date; editing or deleting asks this occurrence versus the whole series; completion is tracked per day; one button clears a day while only skipping recurrent series. Five model tools let the agent read, write, delete, clear and undo plans in conversation.

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

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

Turn a dsh session into a shareable, redacted idea and deliver it to DeepHub friends. Built on DeepSeek Harness.

Select text in the DSH Web GUI and ask about it in place (floating button, or the Alt+Q shortcut): an independent subagent that inherits no parent context answers, streaming into a side card hosted by the native right sidebar, dsh-better-sidebar, or a built-in overlay — and the question can be routed to the main conversation instead.