Plugins

DeepSeek-Harness-Plugin: Anmeldung beim Anbieter, Katalog der Modelle und Weiterleitung der Auswahl über einen nur über Loopback erreichbaren Kanal /model-hub

Modellix-Integration für DSH: schema-gesteuerte Erzeugung von Bildern, Videos und Audio in einem geteilten Design-Arbeitsbereich, ein Live-Katalog der LLM-Modelle sowie native Anbieter für Websuche und Abruf über einen einzigen API-Schlüssel.

Für DeepSeek Harness: Modelle registrieren, bei Porträts helfen und das Agent-Modell aus einem geheimnisfreien Katalog auswählen.

Einheitlicher Plugin-Marktplatz für die DSH-Desktop-(EAC)-Shell, der den kuratierten Katalog, das dsh-Plugin-Ökosystem auf GitHub und die npm-Registry in einem einzigen Shop vereint, mit Quellen-Whitelisting, Konflikt-Vorprüfungen, Test-Boot-Installationsprüfung, manuellen/Stapel-/automatischen Updates und .dshpack-Feature-Paket-Verwaltung.

Ein Klartext-Plugin-Katalog und Profil-Manager für die DeepSeek Harness Web-UI.

In-App-DSH-Plugin-Marktplatz-Panel mit kuratierten und vollständigen Katalogen, Schlüsselwort- und semantischer Suche, chinesischer Übersetzung, Favoriten, Nachverfolgung installierter Plugins sowie Installieren/Aktualisieren/Deinstallieren über die offizielle CLI.

Inoffizieller Cursor-Abo-Chat: Host-eigener CLI-Session-Login, ein angezeigter Modellkatalog und Nutzungsanzeigen des Abos. Cursor-Mitarbeiter werten diese Art privater Client-Nutzung als ToS-Verstoß.

Command-Code-Go-Provider-Adapter für dsh: durchsucht den Go-Plan-Modellkatalog dynamisch und bedient /alpha/generate über die LLM-Schnittstelle des Harness

Plugin-Erkennung über einen generierten Katalog und npm-Installations-Marketplace für DeepSeek Harness

Evidenzbasiertes Betriebskit: sechs rein lesende Tools (Fähigkeitskatalog, stufenweise Workflow-Pläne, Reader für gepackte Skills, begrenzte lokale Gedächtnissuche, Release-Audit für Repositories, Release-Checkliste) sowie fünf gepackte Skills — plant und prüft, schreibt nie remote.

Preset doctor for agent presets: scans home/profile `cordis.patch.yml` declarations and legacy `.agent-presets/` dirs across host lines 0.1.0→0.2.0, shows every detected preset as an official-style card (source/era badges, broken red border, per-finding details, current DSH version + era catalog), and syncs a preset to the current syntax per-card behind an explicit confirm dialog (.bak backup + atomic write; report-level findings are never written — startup scans are report-only). npm: `dsh-preset-doctor`.

Cuts session input tokens three ways, each with its own switch in a panel under the composer: lossless structure-aware compression of tool results on `tools/post-execute`, then a per-tool head/tail elision that always names a recovery path through the shared spill store; tool-catalogue visibility per agent on `agent/created`; and a per-workspace memory document that recall matches against each new message and injects through `agent.inject`, so the transcript is not re-read. Measured 41.76% fewer prompt tokens over 149 recorded requests, with a bundled script that re-measures any profile.

Browse, search and install skills from the public SkillHub catalogue, then enable, disable, update or remove them without leaving Harness. Category chips carry the upstream total for each category; the details drawer has tabs for the file tree, version history, permissions, third-party security-scan results and upstream metrics. An installed skill is written into the harness skill root as an ordinary local skill, and disabling one moves its directory out of that root rather than flagging it.

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。

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

Manage the DeepSeek Harness skill catalog from Settings: list what DSH actually resolves, enable or disable a skill by policy without touching its source file, read and edit SKILL.md, and create, import, or permanently delete skills.

Lightweight zero-dependency memory plugin for DeepSeek Harness: Markdown-file memory store, L0 catalog injection, and 5 model-facing tools.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

Expert market for DeepSeek Harness: WorkBuddy expert/expert-team system ported onto native agent presets, 425-expert catalog installed on demand, capability subtraction, and team delegation tools.

Installs a skill-router skill that semantically searches a local skill corpus on demand, keeping the corpus out of the per-turn model catalog.

The public-apis catalog wired into DeepSeek Harness: search 1716 free public APIs by keyword, category, auth, HTTPS or CORS and call any of them.

Command Code LLM provider plugin adapted for DSH-Desktop 0.7.1: registers a commandcode route, with a live model catalog, reasoning-effort support, and real-time plan usage display.