Plugin

Compressione del dialogo in-place con curva di dimenticanza per DeepSeek Harness: i turni recenti restano verbatim, quelli centrali sono strutturalmente disidratati (senza LLM), quelli antichi si ripiegano in una coppia di riassunti limitata — conversazioni illimitate su un budget di memoria limitato.

Context curation for DeepSeek Harness: content-aware tool-output slimming, dead-log sweep, pinned user requirements and in-flight work, archive-then-compact with an audit trail.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.