Plugins

Text-to-video and image-to-video generation via DashScope Wanx, Volcengine Seedance, Google Veo and OpenAI Sora, with tool results saved to the session workspace and a video gallery (grid, lightbox, download, delete) that survives DSH restarts.

Tavily-backed search provider for native web_search, with a Settings → Plugins card for API key management and toggling DeepSeek replacement.

Zhipu GLM web search provider: registers as `glm` on the ctx.web seam and runs the native web_search server tool through GLM's Anthropic-compatible API (Coding Plan billing).

Configurable web search for DeepSeek Harness using SearXNG, Wikipedia, Tavily, Brave, or Gemini, with per-client engine selection and bounded retries.

Offline, deterministic public API catalog search for DeepSeek Harness, with Chinese and English queries plus exact filters for authentication, HTTPS, CORS, status, source tier, and category.

Lab/project progress management for DeepSeek Harness: 16 progress_* agent tools (item CRUD, day-board pages, daily records, global search, overview, gantt, comments, import/export) plus a 「进度」sidebar tab in better-sidebar hosting the original web UI; data lives in the session project's .progress/progress.json.

Adds parametric CAD modeling, geometry validation, previews, design history, and STEP/STL export to DSH.

User-defined agents with automatic routing, model failover, and squad orchestration: six model tools (agent_dispatch / agent_followup / agent_list / agent_squad / agent_import_skill / agent_upsert), no built-in agents, a native right-tab panel (Overview / Agents / Squads / History), and a floating action ball.

Clean Architecture reference library for DSH: 8 pinned reference repos (Go, Java, C#, Python) indexed into a local FTS5 database, with assertion rules, a review ledger, and a read-only observation panel.

Built-in Obsidian-style knowledge base for DSH: agents distill conversations, documents and web sources into a structured .wiki graph, with retrieval, graph export, note editing, incremental builds and multi-vault management.

A living memory workbench for DeepSeek Harness: watch the Hindsight bank grow (7-day curve, recall heat, timeline) and manage knowledge pages and background tasks, with the local daemon auto-started by the plugin.

Session management for DSH: archive or delete one session, archive/delete all sessions in a workspace, and restore archived sessions from the settings page — archiving backs up workspace metadata and restoring recreates deleted workspace registrations automatically.

Virtual session folders, click-to-move menu, and active task banner for DSH sidebar.

Auto-wakes the main agent after a DSH service restart: compares last-run timestamps, posts a recovery notice with humanized downtime, and delivers it so interrupted work picks itself back up. Runs on plain cordis ctx, packaged-DSH-Desktop ready.

One-click/auto sync provider model lists against /v1/models endpoint.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

Compact DSH wallet panel for any Sub2API-compatible third-party balance site. Uses /v1/usage with a long-lived API Key, auto-discovers configured providers, and shows balance plus daily usage.

Localizes the DeepSeek Harness interface — tool call cards, plugin list, command menu and permission selector display Chinese text while keeping the English originals.

Adds an "Open folder" item to the session-row ⋯ menu in the DSH workspace sidebar, opening the session's workspace folder with the host OS file manager.

A tiny behavioral mood ring for AI coding agents — folds session behavior (consecutive failures, repeated calls, activity) into a four-state Mood (GOOD / CONFUSED / FRUSTRATED / OVERWHELMED) shown as a low-friction session-header status light.

Provider-first three-level model selector for the DSH Web model seat: pick a provider, then a model from that provider, with inline search on both levels, failed-provider retry rows, and a Model · Provider trigger.

Improve the current chat draft before sending with a confirm-before-apply comparison.

Gathers custom plugin settings pages and cards into draggable top tabs under a unified Plugin settings navigation row.

Replaces the model button with a Claude Desktop-style model and reasoning-effort switcher, with per-model effort memory, theme-aware styling, smooth slider feel, rounded track, hover highlight, and pixel-dot animation.