플러그인

Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Tavily search with multiple API keys, key rotation and failover, a usage gauge, and a settings card.

장애 조치가 포함된 2단계 모델 회로 차단기: 반복된 요청 실패 후 모델 또는 프로바이더 전체를 차단하고 다음 요청을 설정된 폴백으로 라우팅

DeepSeek Harness plugin: multi-key pool with automatic quota failover and a usage dashboard for the OpenCode Go plan

DeepSeek Harness용 2단계 모델 라우터 — LLM-Judge 라우팅, 다중 모델 폴백 체인, 지수 백오프 장애 조치, 작업 단위 오케스트레이션(pi-shift-router의 DSH 이식판)

Provider-level web search failover pool for DeepSeek Harness: rotate across 8 free/paid backends (Exa / Tavily / Serper / SerpApi / Jina / DuckDuckGo / SearXNG / Brave) with quota-aware circuit breaking, keeping the native web_search tool. Ships a setting

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.

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.

DeepSeek Harness용 프로바이더 탐색, 매칭, 상태 확인, 출력 전 장애 조치