플러그인

Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure rerouting, and usage auditing for DSH.

Rule-based multi-provider model routing for DeepSeek Harness with pre-first-token failover, cooldown circuit-breaking, usage accounting, and a status API.

Branching surveys in the web GUI: the ask_survey tool with per-option routing, hover insights, Mermaid diagrams, quick one-click answer templates, and resumable banked progress.

User-defined agents with automatic routing, model failover, and squad orchestration: six model tools (agent_dispatch / agent_followup / agent_list / agent_squad / agent_import_skill / agent_upsert), no built-in agents, a native right-tab panel (Overview / Agents / Squads / History), and a floating action ball.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.

DeepSeek-Harness plugin for multi-model orchestration with recursive task decomposition, dynamic routing, quality gates, failure recovery, and KPI reporting.

Branching surveys in the web GUI: the ask_survey tool with per-option routing, hover insights, Mermaid diagrams, quick one-click answer templates, and resumable banked progress.

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.

Adaptive model discovery, evaluation, tiering, and subagent routing for DeepSeek Harness.

Dual-model auto-routing plugin: low-cost direct / high-cost upgrade with an escape-learning closed loop (wrong direct answers auto-learn fingerprints, force-upgrading the same fingerprint next time), persisted and interoperable with the Python ModelRouter.

Free-tier model routing for the DeepSeek Harness (dsh) - discover OpenRouter free models, apply the best free model as agent default, auto-rotate on rate limits; paid config untouched unless asked.

순위 기반 서브에이전트 위임: 역할 기반 모델 라우팅과 페일오버, 경로별 reasoning effort, 모델을 감추는 라벨, 포크 위임, 시각적 경로 편집기.

DeepSeek Harness용 계층형 모델 라우팅: think/build 모델 계층, 비전 위임(비전 모델은 이미지만 설명하고 작업 모델이 실행), 이미지 생성, 고영향 가드.

DeepSeek Harness 비트리 플러그인: 이미지를 Qwen-VL(DashScope) 경로로 ctx.llm을 통해 라우팅하고 텍스트를 반환하여 텍스트 전용 코딩 모델에 시각을 부여

DeepSeek Harness용 프로젝트 독립적 멀티 에이전트 협업 프로토콜: 폭주하는 에이전트 루프를 멈추는 루프 가드, 6필드 핸드오프 형식, 위험 등급별 리뷰 라우팅, 고정된 verify→commit→push→review→close 순서. 같은 규칙을 모든 에이전트에 복사하는 대신 하나의 스킬입니다.

작업-스킬 매칭 메타 스킬. 최소 로딩을 위한 게으름 사다리, 사용자가 편집할 수 있는 라우팅 표, 격리·SkillSpector 스캔·사람 승인 설치 흐름을 갖춥니다.

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

DeepSee: DeepSeek Harness 비전, 멀티 모델 라우팅, 전달 전 Gemini 시각 자체 검증

DeepSeek Harness용 재사용 가능한 Markdown 프롬프트 프로필, 턴별 모델 선택, 인자 치환, 상태 복원 지원

Extra LLM provider routes for DeepSeek Harness: OpenCode Go with per-session x-opencode-session routing, and OpenAI Codex over ChatGPT-subscription OAuth.

Semantic tool routing, skill discovery, and typed System One decisions for DeepSeek Harness powered by TypeSafe Jev.

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.