Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.

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.

Branch from any answer and keep branching at any depth. Recursively isolated follow-ups that leave the main DSH task untouched.

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Session preservation.

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