context-engineering 3

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

Read-only performance diagnostics for DeepSeek Harness: session load (open/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 the /fas

Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section