Memory file duplication causes excessive token consumption

Bug: Memory file duplication causes excessive token consumption

Version: 2.1.150
OS: Debian (Kali Linux)

Problem

Large CLAUDE.md and memory files with duplicate content cause:

1. Context fills to 64%+ immediately on session start
2. Autocompact triggers frequently
3. After compaction, same duplicate content reloads
4. Tokens consumed on each compact/reload cycle

Observed behavior

• ~/.claude/CLAUDE.md (global) contained project-specific content (41K chars)
• MEMORY.md duplicated state already in project's KZP.md
• /doctor flagged files but no automatic deduplication
• Session used 127K/200K tokens (64%) with minimal actual work

Expected behavior

• Warning when global CLAUDE.md contains project-specific content
• Memory index should not duplicate imported CLAUDE.md content
• Autocompact should detect and skip duplicate content

Workaround

Manually trimmed:

• Global CLAUDE.md to 1K (user prefs only)
• MEMORY.md to index-only (no state duplication)
• Removed redundant @imports

Token impact

~30K tokens wasted per session on duplicate content loading