mirror of
https://github.com/shareAI-lab/analysis_claude_code.git
synced 2026-06-20 20:23:36 +08:00
The compact tool schema declares a "focus" parameter ("What to preserve
in the summary") but the handler ignored it entirely -- the parameter
was never passed to auto_compact(). Now the focus value is captured from
block.input and included in the summarization prompt so the LLM knows
what details to prioritize when compressing the conversation.