L0~L3 分层蒸馏记忆插件 for DeepSeek Harness：自动捕获对话（L0）、抽取原子记忆（L1）、整合场景块（L2）、蒸馏核心画像/团队方法论（L3），并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

DSH permission-gate for the DeepSeek Harness 0.1.5 line: a single self-sufficient, deterministic-first, fail-closed gate covering P0 hard-deny -> P1 session grant -> P2 static rule (allow/deny) chain -> P3 optional LLM semantic classifier -> P4 ask, with

DSH Web 插件：会话管家（合并包）—— 会话历史文件（归档浏览与清理）与健康检查（体检 → 处方 → 出院），外加独立 FTS5 会话内容搜索索引（标题/内容双模式、增量同步、非破坏性整理与快照导入导出）。不碰会话日志、只做可逆处置。

Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, writes take effect immediately, signal-driven injection, no embeddings

Git status badges for DeepSeek Harness: an input-row chip and a sidebar session-row action glyph, on every install — no patch and no manual step. Event-driven freshness over SSE.

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.