Plugin

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

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.

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.

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.

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.

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).

Un unico plugin per DeepSeek Harness per ogni provider pi-ai, incluso l'OAuth per abbonamento

Provider di fetch HTTP(S) resistente a SSRF per DeepSeek Harness

Budget fail-closed per passo, chiamata a strumento e token del provider, per turno, per DeepSeek Harness

Provider OAuth di OpenAI Codex e adattatore di modello per dsh-oauth e DeepSeek Harness

Accesso web per DeepSeek Harness — ricerca/fetch multi-provider su ctx.web, più estrazione da GitHub/PDF/YouTube

WebSearchProvider basato su Bocha e bundle di profilo installabile per DeepSeek Harness

Scoperta dei provider, corrispondenza, controlli di salute e failover pre-output per DeepSeek Harness

Provider di ricerca basato sull'API Brave Search per l'interfaccia di capacità web di DeepSeek Harness (ctx.web). Una ricerca è una richiesta HTTP - nessun turno del modello