Plugins

Korean (ko) language pack for the DeepSeek Harness desktop and web GUI: registers the ko locale catalog entry and serves Korean copy for every built-in client dictionary.

Local OCR using Apple Vision on macOS: text from screenshots, photos, and scans, with no install, no network and no API key.

Rewrites your composer draft in the voice of a chosen character card before it is sent, using the model the current session is already on, with an optional review panel and a local check that reports any identifier or path the rewrite dropped.

Six features in one bundle: a desktop pet in its own transparent always-on-top window (codex-pets.net marketplace), a global wallpaper (wallhaven.cc marketplace or a local image), the Session-header Open In… button with the desktop-build fixes, a codeg-st

Liuyao divination in one click — ask a question, cast the six-line hexagram, and let AI interpret it for you; every cast is saved locally.

Bring a DSH plugin repository's build and release pipeline into the app: a sidebar panel listing each repository's latest workflow run, its releases, and how far the local checkout has drifted from the last release, with buttons to trigger a build, cut a release, publish a draft, re-run, cancel, or read the failed-step log. Drives the workflows through the machine's authenticated gh CLI, so the plugin stores no credential of its own, and which repositories are tracked lives in a config file rather than the package.

Full-duplex voice mode for DeepSeek Harness 0.2 desktop: streaming ASR to draft, sentence read-aloud, barge-in, live captions, plus an in-app settings page. An unofficial compatibility fork of dsh-voice-mode 0.7.15.

Local AI-agent request-log panel: aggregates local logs from atomcode, codebuddy, workbuddy, claude, codex, codearts, gemini, cursor, kimi and dsh, and shows per-round latency, tokens, cache, context and tool calls.

Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-over model pool (multi-account rotation, live credits, daily check-in and model catalog).

Per-turn and per-session estimated cost in the DSH Web UI, computed from provider-reported token usage in four buckets with the built-in official DeepSeek CNY peak/off-peak card — peak hours are Monday-Friday 9:00-12:00 and 14:00-18:00 Beijing time, weekends and Chinese statutory holidays are off-peak all day. An optional local JSON rate table overlays prices for other or self-hosted models, and models without a price show tokens only.

DSH 循环护栏：① assistant-stream 字符重复检测（可 abort）；①b 低多样性高重复（末窗 + 滑窗两支，抓「带噪声的交替空转」与「正常推理里夹一段空转」——① 线的精确匹配结构上抓不到它们）；①c ① 线命中时注入「停止」类词 + 预注册观测（注入是温和动作，先于掐断）；② 行动层「无进展」停滞检测；②b 同参工具调用连击（按**动作参数**判定，忽略 description 之类自注）；③ 反复卡住达阈值 ⇒ agent.cancel() 真切断；⑤ 零正文 turn（只有思考

Localizes known DSH system instructions and runtime reminders into Simplified Chinese, trims tool-related guidance to visible tools, and provides editable translations and component toggles while preserving tool names and parameter schemas.

Full edition of the motor-design AI plugin for DeepSeek Harness: adds the L1 (Ansys RMxprt) and L2 (Motor-CAD) precision layers on top of the L0 millisecond-level broad filter, completing an end-to-end chain from requirement parsing to parameter identification, candidate matrix, L0 pre-screening and L1/L2 verification. Mutually exclusive with dsh-motor-ai-l0 (uninstall l0 first); the shared core @wangxue98/dsh-motor-ai-core installs automatically. L1 needs Ansys AEDT (RMxprt) and L2 needs Motor-CAD installed locally. Distributed under the PolyForm Noncommercial licence; L1/L2 require an activation code. Telemetry is on by default: per-tool usage counts and design-experience samples that the author describes as desensitized are sent to the author's server at wangxuewangxue98.deno.net, and fault assistance can upload fault reports; switch them off with telemetryEnabled, designExperienceUpload and faultAssistEnabled in the plugin config.

dsh addon: a Local Models settings tab that starts and stops a llama-server child process living with the dsh host process.

Local decision-layer plugin for DSH: a fail-closed command approval gate and ask/gate tools backed by a 144.3M on-device model. Needs a separate local decision service: `pip install phocinae-server`, then download the ~330 MB weights and keep the service running; without it the tool returns `PHOCINAE_SERVICE_UNAVAILABLE`.

Search and read local Claude Code, Codex, Antigravity, Grok and DSH sessions from the 1session CLI or DSH Web history browser.

DSH slash command /commit: stages all changes, summarizes the staged diff with the session model, and commits; no browser UI required, with a local fallback when the model call fails.

Imports a proxy subscription, supervises a local mihomo core (proxy-provider plus a url-test group), and fetches direct-first with automatic proxy fallback and per-host routing memory; exposes one proxy_router tool (status, start, stop, test, fetch, routes, forget).

Local-folder knowledge base for DSH: builds a SQLite FTS5 index over Office, text, PDF and scanned files, ships five tools (kb_search / kb_read / kb_list / kb_status / kb_session) plus a Web panel, and retrieves or syncs only when the user explicitly asks.

Use local Ollama in DSH with Ollama native API and params support.

Bridge between DeepSeek Harness and a local desktop pet: session event push, per-session progress buckets, and 'user has actually seen it' notice acknowledgement.

Permanently delete a DeepSeek Harness conversation and every local copy of its data: session log, derived caches, workspace index entries, spill files, and unreferenced attachments.

为短上下文窗口的对话提供更轻量的 Agent 预设，能降低78%的固定开销。由 Deepseek 制作

Chain-of-thought panel for the DSH Web right sidebar: folds the live reasoning stream of each session into turn → step groups carrying the reasoning text and the tool calls made in that step. Only the newest turn is expanded by default and earlier turns collapse to one line; steps are grouped into activity phases by a local rule, the step waiting on a tool is marked, tool failures show their reason, full reasoning text is fetched per step on demand, an all-turn directory searches turn titles, user text and turn numbers locally, and a whole turn can be summarised into a Chinese title with one model call.