12 results
Verdict-based compaction engine for DeepSeek Harness: replaces the lossy compaction summary with fast per-call keep/truncate/drop decisions, keeping everything else verbatim (port of tamaratran/fast-jev-compaction)
树形任务流：把多步任务组织成目标→任务→子任务三级树，节点完成时由 AI 提交结果，插件随即把该节点的执行过程从上下文里折叠掉，只留下结果。
DeepSeek Harness dynamic context pruning plugin (model-driven context management)
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
DSH 上下文管理插件：任务边界、项目帧、自动判别与上下文优化（开发中，R2 判别域 P8–P14b1 已施工）
DSH 上下文检查点：每步注入真实占用条、模型可显式预约 checkpoint+压缩、压缩后在回合边界执行并自动继续同一任务
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
DSH plugin: Codex-style context management — token-budget notice, model-facing new_context, and handoff reset instead of summary compaction.
Summary-free context window rollover, model-authored notes, and scoped raw history lookup plugin for DeepSeek Harness (DSH)