플러그인

점진적 공개 방식의 MCP 게이트웨이: `mcp_search`로 대규모 원격 카탈로그를 검색한 뒤, 지연 연결과 제한된 캐시로 `mcp_call`을 통해 정확한 스키마를 호출

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

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.

Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section

Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via the /fas