Plugins

Compressão de diálogo in-loco por curva de esquecimento para DeepSeek Harness: turnos recentes permanecem verbatim, turnos médios são estruturalmente desidratados (sem LLM), turnos antigos se dobram em um par de resumos limitado — conversas ilimitadas em um orçamento de memória limitado.

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.