Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.
View on GitHubBrowse similar plugins
Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.
See the GitHub repository for installation instructions — this plugin does not publish a standard install command.
中文说明：Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.（安装方式请参考 GitHub 仓库说明。）