dsh-skill-switch
Windows Junction-based global Skill switcher for DeepSeek Harness Web.
192 results
Windows Junction-based global Skill switcher for DeepSeek Harness Web.
Sync cc-switch provider profiles (Claude Code / Codex relays) into DeepSeek Harness as llm-pi-ai routes, credentials stored via the DSH credential seam.
Switch between Chat and Agent without leaving your DeepSeek Harness session.
Cross-session memory cue bank for DeepSeek Harness: builds a persistent event-cue library (keywords, user language idiosyncrasies) and re-activates remembered event details on topic switches, mirroring human episodic recall.
DSH plugin: right-click a folder in Windows File Explorer to open it as a DSH workspace (launches DSH if needed, creates the workspace, starts a session, and switches the DSH page to it).
One-click DSH background switcher backed by local Wallpaper Engine images/videos (WE Web API first, Steam workshop/myprojects directory scan fallback)
DSH web plugin: GitHub-style daily token-usage heatmap on the new-session screen with a selectable calendar-year view, green/blue color schemes and a display switch (设置 → 插件 → 插件配置), plus today / this-month / all-time totals.
DSH plugin: sync cc-switch provider balances and track token usage & cost by day/month/total with relay-aware currency settings.
DeepSeek Harness LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint: per-model multimodal switch, fully configurable reasoning efforts, and a web settings page (client plugin) for editing the deployment from the frontend
A pure runtime that routes DeepSeek Harness sessions to pluggable loop engines by agent-preset. Ships no engine; downstream plugins register engines via ctx.engineSwitch.
IDE-style workspace switcher sidebar for DSH (DeepSeek Harness): floating workspace dropdown, session filtering, done/pending status lights, workspace & session search, and workspace rename/delete/archive/add.
DSH web plugin: theme customization placed under the built-in Appearance (外观) settings. It reuses the Appearance light/dark switch and lets you adjust accent / background / foreground / contrast for the active theme, applied live through DSH theme token overrides.
Overleaf tab for dsh-better-sidebar: account login via direct-CDP browsers (third-party Chromium supported), project list/switch, workspace mirrors under <workspace>/overleaf/, git/API sync, and file preview through the sidebar workbench
Agent answer sound effects for DeepSeek Harness web: play start/done/error tones on answer lifecycle, with per-kind volume, custom audio file and a master switch in settings.
Run Claude Code, Codex, Pi, or the built-in loop side by side in one dsh — pick the engine per session, switch without restarting, keep one session store, history, and trace.
DSH plugin: real-time API balance in the sidebar with provider switching (DeepSeek / Zhipu GLM / OpenRouter / Tavily), peak/off-peak pricing, per-session and daily cost tracking, and configurable spending limits.
Provider failover for DeepSeek Harness: on rate-limit (429) or quota exhaustion, automatically switch between providers with configurable per-provider models, fall back to the last one (e.g. DeepSeek official), and show a visible notice in the UI.
DSH web plugin: a Git branch pill in the session header that shows the current workspace branch and switches branches from the UI
Windows/WSL environment switcher for the DSH web UI (coexistence model; mid-column sidebar entry, collapse-aware)
DeepSeek Harness Windows desktop companion: tray icon (whale), desktop shortcut, login auto-start that opens exactly the client you chose (desktop app window or web browser), and one-click desktop/web switching (local Edge/Chrome app mode).
One-click web search-engine switcher beside the DeepSeek Harness model picker.
DSH web plugin: switch the current session's agent preset (mode) at any time, even after the conversation has already started - the stock UI refuses that. Provides a session-header dropdown plus a fenced /preset-switch/api route.
DeepSeek Harness plugin: switch the current conversation's agent preset (mode) after the model finishes answering, and keep chatting in the same session
Save and switch model and reasoning-effort presets in the DeepSeek Harness composer.