jasen215/dsh-continual-harness

README excerpt

dsh-continual-harness English 中文 A continual self-refinement plugin for DeepSeek Harness: one plugin gives the agent a closed loop of persistent memory + periodic review-and-refine + cross-session shared knowledge + automatic rollback on failure (plan → validate → apply → rollback). The design is inspired by the open-source prime-agent from Prime Intellect, a self-improving coding harness. Capabilities A single npm package ( dsh-continual-harness ) takes effect through the following extension points once mounted: Capability Mechanism State projection (inject harness context each step) agent/pre-step waterfall listener; incremental injection when the content digest changes Review and automatic refinement session/event listener on turn interval / compaction end; runs LLM review → plan → apply automatically Manual refinement tool Registers the harness refine tool (directly callable by the LLM, supports rollback) Memory lifecycle Manual archive/unarchive/pin through refinement metadata; archived entries are hidden from injection and skill materialization Ranked injection Queries the latest effective direct-user message (up to 400 chars), ranks title matches above content matches, then …

Category