Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills 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.

Model-controlled context blocks for DeepSeek Harness PTC mode

Cross-session memory for DeepSeek Harness — plain markdown files, no database, no worker.

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

One chat for everything in DeepSeek Harness (DSH): no more hunting for old conversations. Each message goes to the topic it belongs to, with its own context.

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

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.