플러그인

Read-only page structure for DSH, attached to the CUA browser: table coordinates, shadow DOM fields, code blocks, and confidence labels.

Reads a running workbuddy2api-panel over its HTTP API and syncs its models into the DSH model picker with credit multipliers, CN/international realm labels and per-model reasoning-effort levels; also shows remaining credits and usage in a settings page and a sidebar badge.

Four palettes for the DeepSeek Harness web UI — solid, glass, volume and neon — each with light and dark halves. Neon adds a scene light field with a 46px circuit grid, a laser scan that sweeps the conversation column only while a turn is running, HUD-style workspace labels in the sidebar, embedded MiSans Latin chrome type, and a 125% sidebar type scale that stays fixed while the conversation area zooms.

Offline Beijing-time peak/idle indicator below the conversation composer, with a 2026 calendar, uncertainty labels, and brief peak reminders; no API key or runtime network access required.

DeepSeek Harness Web에서 보이는 중국어 UI와 콘텐츠를 번역합니다. 세션 제목, 워크스페이스 이름, 메시지, 검색 결과, 그리고 선택적으로 동의한 플러그인 텍스트에는 브라우저 로컬 OPUS-MT 모델을 사용하고, 원격 번역은 허용 목록에 있는 UI 레이블로 제한합니다.

순위 기반 서브에이전트 위임: 역할 기반 모델 라우팅과 페일오버, 경로별 reasoning effort, 모델을 감추는 라벨, 포크 위임, 시각적 경로 편집기.

관련된 DSH 세션 브랜치에 대한 사람의 결정(유지, 폐기 또는 사유·레이블·외부 링크를 붙인 후속 조치)을 추적합니다.

Select completed assistant text, add comments, and send compact annotation labels with source navigation in official DSH 0.2.1-rc.2 Web; no host patches required.

Plugin Steward adds a plugin panel to the chat composer for managing the installed DeepSeek Harness plugins: list them, switch them on or off, edit a plugin's settings, hide one plugin's tools or MCP servers from a single conversation, and have the model write short Chinese labels for installed plugins by reading their own README and package files.

IDEA-style Git workbench for the Web UI: commit graph with lanes and ref labels, log filters, commit details, split and unified diffs with per-hunk staging, a fine-grained zero-context mode, local changes with amend and sign-off, rename-following file history, per-line annotate, stash, branch operations, compare, tags, an interactive rebase planner and conflict resolution. Records which model produced a commit by stamping an Assisted-by trailer from the live session, and renders any existing commit trailers as chips, so AI-authored history stays traceable.

Lets the agent see the compiled page: renders any page to an image, resolves a PDF point or a text anchor to the exact source line through SyncTeX (and says when a rule is drawn by a package rather than by the body, which is where naive locating is wrong), diffs a page against the previous build so an edit is visible, audits every page for holes the edit introduced, and checks that numbered labels still read in order.

Reads a video or audio file into metadata, sampled stills, subtitles and a multilingual speech transcript with speaker labels, captures the live desktop as frames or a recording, and installs its ffmpeg/whisper.cpp/sherpa-onnx toolchain on first use with per-file sha256 checks; all processing stays local. Automatic toolchain install and desktop capture currently support Windows x64 only, so elsewhere ffmpeg and model paths must be set manually.

Publish size check skill: verifies a deliverable's geometric specs against a target platform before publishing - pixel dimensions, aspect ratio, dpi, file size, format, physical print width and colour mode. Geometry only: it does not review content compliance (QR codes, text-to-image ratio, copyright and prohibited content are out of scope). Pure Python standard library, no third-party packages, and inputs are never modified. Python 3.8+. Covers 10 platforms and 20 slots with per-platform confidence labels - WeChat MP, Xiaohongshu, Bilibili, Zhihu, Weibo, Douyin, WeChat Channels, journal submission, print and client delivery - and resolves a platform by id, Chinese name or alias with fuzzy matching. Two trigger modes: asked directly, or as a parasitic self-check that runs by itself once an image, poster, chart or export workflow has written a file and the user mentioned a publishing target, reporting in one line when everything passes and only expanding when something is wrong. For journal submission and print it judges by physical width (pixels / dpi), which catches files whose dpi metadata passes but whose actual printed size is too small; for multi-image posts it checks whether the whole set is consistent and names the odd one out rather than listing every file.

Audits JLCEDA (EasyEDA) .enet netlists for broken net labels, dangling nets, power-rail orphans, conflicting pin polarity, and full-differential-amplifier feedback wiring.

Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.

Ctrl+F find-in-session for the conversation, powered by the session store rather than the DOM - labels every hit by source (you / assistant / reasoning / tool call / tool result / system), groups results by turn, merges identical snippets, offers prose-vs-everything scope, regex / case / whole-word options, highlights all matches, and copies or exports the result set as Markdown.

Better Right-Click: right-click menu on file references in the DSH transcript. Copies the absolute path, reveals the file selected in Explorer by reusing and focusing an existing window, and lists every app registered for that file type so you can open it with the one you want. Menu labels follow the DSH display language (Chinese and English). Windows only (Explorer reveal and the registered-apps list use PowerShell).

AList v3 file management: browse, search, upload (streamed and multipart), offline downloads, archive listing, task polling and control, plus admin tools for storages, users, roles, meta rules, settings, search index, shares and labels - 75 tools in total; every write goes through the approval flow and passwords are never read back.

Subagent model control: a Jev classifier labels each turn, and the subagent request itself is rewritten to the provider, model and reasoning effort that the label maps to, at the agent/request hook; a per-session inherit/auto/manual selector, one prompt per role injected ahead of the task, and offline replay of past verdicts.

Thesis and empirical-analysis workbench that drives IBM SPSS from the conversation: spss_check (environment self-check), spss_variables (list .sav variables with labels, types, measurement levels, case counts), spss_data (sample case rows to inspect missing and outlying values), spss_run / spss_run_file (execute SPSS syntax or an .sps file, relative CD and GET FILE paths auto-rebased), and spss_analyze (one-shot frequencies, descriptives, crosstabs with chi-square, t-tests, one-way ANOVA, correlation, linear regression). Results come back as structured tables extracted through OMS. SPSS 25-31 is auto-detected; the bundled MCP server is zero-dependency stdio.

Pins sessions into a single Pinned section above every workspace group in the Web sidebar without touching the stored session order — the pin is a flag kept in the host settings document, and a right-click row menu adds rename, pin, fork, archive, delete and copy title or session id, with labels that follow the GUI language.

Quick sticky notes with colored labels, pin, timed reminders, and password protection for DeepSeek Harness.