Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea appli

by peterwangze

DSH (DeepSeek Harness) plugin: unified default reasoning level (thinking effort) for all models — per-model defaults with capability probing, live call statistics, one-command install via dsh plugin

by d3vmeh

DeepSeek Harness plugin: keep a local model's context at a size your GPU handles well (measured prefill speed, hard ceiling, early compaction)

by falling-ts

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‑win

by feiyang-dev

DeepSeek Harness 用量与消耗插件（dsh-usage-plugin）—— 每次调用的 token 用量/缓存命中统计、峰谷计费、余额查询、CSV/JSON/PNG 导出，可经桌面端一键安装或命令行 dsh plugin add 安装。

by Leitarkkk

DeepSeek Harness plugin that auto-nudges agents to consult docs or web search when local trial-and-error becomes costly. DeepSeek Harness 插件：当本地试错成本升高时，自动注入检索提示，引导 Agent 查阅文档或联网搜索。