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.
Multi-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线：多智能体部门长线任务解决框架，对抗AI幻觉，以学术研究为验证场景。
一条命令备份/恢复 DeepSeek Harness（dsh）的全部数据：升级快照、会话日志体检修复、迁移预检、救援通道、凭据脱敏、GitHub 同步。 One command to back up & restore all of ~/.dsh: /backup, auto-backup, upgrade snapshots, session doctor & repair, migrate precheck, rescue console, credential redaction.
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.
Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command, reflex arcs fire with zero model calls, memory consolidates while idle, every failure is attributed before retry. Reproducible offline, MIT.
Use DeepSeek Harness from your phone or another computer. Host: mobile UI, pairing-code gateway, PWA and Web Push, plus sharing chosen sessions. Client: those sessions appear in another DSH desktop's sidebar. 手机和另一台电脑都能安全远程使用 DSH
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness 辅助模型插件：为视觉理解、上下文压缩、审批审查、子代理、会话标题与图片生成提供独立的模型路由、工具与系统提示，全程不触碰主对话模型。
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。
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.
Turn your devices into a fleet — dsh plugin for decentralized multi-device collaboration: mDNS discovery, key pairing, SSH direct exec. Tools auto-register for dsh agents.
Prompt enhancement plugin for the DeepSeek Harness web GUI: one-click rewrite of the composer draft into a structured prompt, with preview, fill-back, and undo.
一个 DeepSeek Harness（DSH）插件： 在 Web 输入框的工具行中添加一个 ✨ 图标按钮。点击后选择打磨风格，已接入的大模型 会把你草稿中的提示词改写得更专业、更易被 AI 理解 。A DeepSeek Harness plugin: icon-only composer button that rewrites your prompt via the connected LLM (balanced/concise/detailed/code styles, i18n)
