Plugins

A Go + WebView2 desktop shell for the DeepSeek Harness Web UI (dsh web). Prebuilt Windows x64 binary bundled in the package; no install script and no runtime download needed.

Primary-controlled deliberation and opt-in masked review for DeepSeek Harness

DSH plugin: manage dbhub database MCP servers from the settings panel; starts dbhub in-process (no npx) and exposes its tools via dsh-mcp-client.

Visual Kanban board for DeepSeek Harness with Gitea-backed tasks, workflow columns and a dedicated agent session per task.

XiaoShuang desktop pet for DSH: six-layer memory, persona injection, mood-driven video avatar, manual emotion menu, and TTS replies.

Provides a secure reverse proxy, enabling DeepSeek Harness to be accessed remotely and to converse with AI anytime, anywhere.

Spec-driven service forge and integrated operations workspace for DeepSeek Harness.

Windows-only tray monitor for DeepSeek Harness: deploys and manages the standalone DshTaskWatcher tray app - four-state tray icon (gray=disconnected, green=idle, amber=running, red=attention), a per-task panel with live duration/tps/tokens, and completion & outcome notifications. Start/stop switch in Settings > Plugins; the watcher is an independent process that survives DSH restarts.

Poll Feishu (Lark) group and direct chats through lark-cli, extract candidate tasks with a review workflow, and two-way sync them with the task-board plugin, with a floating browser panel and one-click device-flow authorization.

Drop-in web_search provider that follows the session's routed model: a runtime-editable priority chain with three wire dialects (Anthropic web search, OpenRouter online, Zhipu bigmodel), per-route endpoints and credentials, a Settings UI panel, local JSONL call audit, and built-in official fallback.

Prevents concurrent-write session corruption: takes a per-session advisory lock on session start and every step, so a second dsh process fails loudly instead of writing a duplicate-seq gap; dead owners are taken over automatically.

Auto-renames DSH sessions with LLM-summarized titles: runs after the first prompt and on /handoff, or manually via a header button or /autotitle, with configurable title language and max title bytes.

Scan, view, and safely clean local AI terminal session histories (Claude Code, Codex CLI, WorkBuddy, DSH) from a settings card — quarantine-first with SHA-256 manifests, one-click restore, audit log, and phrase-confirmed hard delete.

Force the model to write all replies in a chosen language (Simplified Chinese by default) via a system-prompt section, switchable anytime with a tool.

Grouped provider and manufacturer model selector for DeepSeek Harness, preserving provider/model routes and reasoning levels.

Shows MiniMax Token Plan usage in the Settings page through webServer routes and reads either subscription key name from environment or credentials file.

Live DeepSeek API balance in the sidebar footer plus an always-visible bottom-right pill: status dot and amount, refreshed every 60 seconds, the API key is read from the local credential store and never embedded.

Adds touch-friendly navigation, layout refinements, and standalone PWA styling to the existing DeepSeek Harness web interface.

Browser tab status indicator for dsh web: paints the document favicon from the session list (blue spinning while work runs, amber while waiting on the user, green when finished).

Dependency graph inspector for DeepSeek Harness: snapshots the live Cordis plugin/service topology into a zoomable browser panel with graph-theory metrics, plus a graph.render tool for the model.

DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.

Plugin inventory manager for DeepSeek Harness Web: table view of installed plugins with status filters, enable/disable switches applied via HMR, config viewer/copy, uninstall and npm update reminders.

Workspace-scoped Git graph with history search and diffs, multi-worktree WIP and agent-session views, and guarded Git operations with recovery refs.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.