플러그인

DSH 세션과 승인된 Agent Team Room 간의 비동기 LLM 요약 컨텍스트 중계, 즉시 스냅샷과 예약된 요약 제공

읽기 중복 제거가 적용된 증분 파일 마운트: 마운트된 줄 범위는 모델에 다시 전송되지 않으며, 디스크 변경 시 무효화 후 재마운트, Mounted Files 탭과 토큰 절감량 집계 제공

DeepSeek Harness 에이전트 기능을 MCP 서버로 노출해 외부 MCP 클라이언트(예: Hermes)가 Harness를 구동해 코딩 작업을 수행하도록 함. Hermes = 두뇌, Harness = 팔

명세 산출물, 스킬, 명령어, 목표 기반 구현, 작업 진행 컨텍스트 추가

Drive Origin scientific plotting from DeepSeek Harness AI chat via MCP: write data, plot line/scatter/column, export PNG/SVG.

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

Sidebar meters for DeepSeek Harness Web: a DeepSeek account balance bar (orange, with a low-balance alarm) and a conversation context-usage bar (blue), rendered above the plugin store with a hover detail popover.

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

DSH plugin: automatic dual-peer Honcho v3 memory, contextual recall, search, reasoning, conclusions, and health diagnostics

MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free context in real time; optional AI middle layer (mcp_search/mcp_call) calls disabled servers on demand, with state-based visibility filtering that keeps user-enabled servers visible.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Minimal-compatible first turn for Web root sessions: starts with persistent bash and str_replace_editor, removes automatic workspace and skill context, then restores the selected preset after the first tool call or reply; includes a persistent composer toggle.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Right-side prompt toolbox panel with 24 built-in deep templates plus user-defined ones, accessible via the /prompt slash trigger and a context-aware floating suggestion card; one-click inserts the selected prompt into the composer.

DeepSeek Harness용 GPU 인식 실행 레이어: gpu_status / gpu_exec / gpu_run_bg 도구, 단계별 GPU 컨텍스트 주입, CUDA_VISIBLE_DEVICES 카드 자동 선택

DeepSeek Harness용 컨텍스트 압축 스킬 -- 지능형 대화 요약

DeepSeek Harness용 영구 장기 페르소나 메모리: MEMORY.md/USER.md 저장, memory + memory_search 도구, 요청별 컨텍스트 주입, 비밀 정보 스캔. pi-hermes-memory의 설계 철학을 이식

DeepSeek Harness Web 프로필용 논리 호출 컨텍스트 분류 체계

claude-mem을 통합하는 DeepSeek Harness 플러그인: 로컬 claude-mem worker의 HTTP API를 통한 조회, 컨텍스트 주입, 수동 저장, 세션 생명주기 관리