Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace recall - and sliding-context awareness (compaction summaries in recall/search, compaction notice with one-click /compact fill).
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B/Flash-Next): per-request thinking budgets, a compaction backend that stops burning the output cap on thinking, and a settings tab. 本地 Qwen3.8 线的 DSH QoL 插件：逐请求 thinking 预算、不再把输出帽烧在 thinking 上的压缩后端、设置 tab。
Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。
Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.
Make your dsh ready for serious coding. (Tools x Schemas)^REPL. skill://, ctx://, agent://, dvc://, dsh://, IPython REPL, Context as Variables, cross compaction recallable, full context revive. hash-edit, dvc://browser, subagent as a function, workflow as a function.
DSH plugin for agent-driven span compaction: compress chosen conversation spans into self-written checkpoints instead of the official head-anchored full-context sweep.
Game-style floating HUD for DeepSeek Harness: balance HP bar, context MP bar, official peak/valley pricing with countdown, auto-compaction, memory-carrying new conversation. ?????? HUD ??
Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.
