llm-cache

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.

Five-decimal cache-hit readout beside the chat stats line for the DeepSeek Harness Web GUI (dsh-plugin)