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.
Claude Code-style @path imports for DeepSeek Harness: expands @imports in AGENTS.md/CLAUDE.md and injects referenced files into context at session start
DeepSeek Harness(DSH)第二大脑载入器:把有硬上限、带时间戳的脑快照(身份+状态指纹+未决项+指针与边界)注入每个新会话;只读、零写入、fail-loud、零依赖。 | Second Brain loader for DSH — a bounded, timestamped snapshot of your local brain in every session prompt; read-only, zero-dependency.