Plugins

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.

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.

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.

Composer cost chip: prices the current session DeepSeek API spend message-by-message with the official pricing table (incl. the 2026-08-17 peak/off-peak policy); hover for the breakdown, today (DSH) total and account balance. DeepSeek models only.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

Session cost estimate in a status bar at the bottom of the conversation (per-model token pricing, CNY) plus the live DeepSeek account balance via the official balance API.

Official-style composer model trigger with a floating reasoning-effort slider popup.

Animated Claude-style reasoning-effort slider and model picker that replaces the native DSH model selector.

No-setup mode for the DSH web UI: hides advanced surfaces, auto-applies best defaults (chat mode, full access, account balance), and one-click role-play personas (maid/butler).

Windows desktop launcher for DSH with a whale-girl icon, background server startup, and a Chromium app-mode window without browser chrome.

Session header badge showing DeepSeek peak/off-peak status, per-model token prices on hover, and real session/turn costs from actual usage.

Fournisseur OAuth OpenAI Codex et adaptateur de modèle pour dsh-oauth et DeepSeek Harness.

Fournisseur de recherche adossé à l'API Brave Search pour la jonction de capacité web (ctx.web) de DeepSeek Harness. Une recherche = une requête HTTP — pas de tour de modèle.

Passerelle locale de revue de code par IA : passe en revue un diff d'espace de travail/branche/commit via ocr.js géré, en renvoyant des constats structurés avec des statistiques de tokens ; le mode gate échoue en cas de constats.

Prenez le contrôle de vos panneaux tmux : list/send-keys/capture, exécution de tâches longues dans un panneau en mode watch, et commandes destructrices soumises à approbation.

Hooks de cycle de vie façon Claude Code : des commandes shell configurées s'exécutent avant/après les appels d'outils du modèle avec une charge JSON sur stdin ; un code de sortie non nul avant l'outil bloque l'appel.

Mémoire inter-sessions pour le modèle : recherche en texte intégral dans toutes les sessions passées (SQLite FTS5 via ctx.sessionQuery) et ramène les extraits les plus pertinents dans le contexte actuel.