Plugins

Read-only side-by-side comparison of related DeepSeek Harness conversation histories, including messages, tool calls, responses, timing, and usage.

Track human decisions for related DSH session branches: keep, discard, or follow up with reasons, labels, and external links.

Create/modify/inject test assistant messages and import/repair session.jsonl(.zstd) session logs into new sessions.

Archived conversations list in the sidebar footer with read-only previews of the most recent messages, for sessions the product deliberately keeps hidden and unreopenable.

Automatically fills in reasoning-effort levels for models from unofficial (custom) providers, with data sourced from models.dev.

A GUI subagent-model selector beside the main model seat: pick a model and reasoning effort per session, applied to every in-process subagent.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.

Unofficial Cursor subscription chat: Host-owned CLI session login, a displayed model catalog, and subscription usage rails. Cursor staff treat this class of private-client usage as against ToS.

Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.

Font system plugin: OFL webfont presets served offline from the plugin, user-imported custom woff2 fonts, and a ctx.fonts registry other plugins can extend.

API key rotation pool for your LLM providers: auto-discovers providers from settings, per-provider multi-key round-robin, failover on 401/403/429, and cooldown recovery.

Animated wallpaper plugin with 8 canvas backgrounds (particles, meteors, starfield, waves, rain, bubbles, matrix, aurora) plus custom video import, and speed/density/opacity/blur sliders with localStorage persistence.

Digital arcade HUD skin: neon cyan/violet/magenta palette, Fusion Pixel fonts, animated sprites (city backdrop, data core, mascot), custom crosshair cursor; light and dark themes follow the system.

Dracula theme plugin for the DSH Web GUI: the classic dark palette and the Soft variant registered into the native theme runtime, one-click switching with a persisted choice.

Anime skin pack for the DSH Web UI: five AI-generated HD themes (Ninja, Sakura, Bamboo, Ronin, Ryujin) with per-theme accent palettes, a top-right shirt-icon switcher, and an adjustable transparency slider.

Anthropic Sans, Serif, and Mono fonts for the DSH Web UI, with Source Han fallback for CJK.

Moonrise dark theme for the DSH Web UI, with deep indigo surfaces and warm amber accents.

Bottom-right 余额 badge for the DSH Web UI: on expand it fetches the currently-selected provider's OpenCode Go plan limits or DeepSeek prepaid balance, plus local token usage and pricing-based spend estimates.

Floating cost crystal for the Web UI: balance card, real-time tok/s, peak/off-peak billing countdown, last-24h spend, and a 🔮 next-message cost forecast, all timezone-aware.

Settings-page usage dashboard: per-provider/model token summary across all sessions, with today/7-day/30-day CSS-bar trends and a cache-hit rate.

DSH usage and balance panel with official live balance, per-event official peak/off-peak pricing, all-channel spend estimates from daily balance snapshots, and a Codex-style 12-month token activity timeline. Fork of Ychris12138/dsh-usage-stats.

MiniMax token-plan quota dock for the Web UI: a drop-shape 5h-usage % chip in the conversation input area, click for a detail panel listing every model's 5h & weekly usage and reset countdown, auto-hidden when the active default model is not a MiniMax model.