fix(memo): avoid stale auto-extract dedup and optimize byte trimming

[fennoai]

Requested by @Yumiue

Summary

• Fix stale auto-extract dedup tracking when the new entry is trimmed out by index limits
• Reduce index byte-trim cost by replacing repeated full re-render loop with binary-search trimming
• Align memo_recall keyword schema description with actual content-matching behavior
• Add regression tests for dedup tracking and byte-trim behavior

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

❌ Patch coverage is 87.50000% with 4 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
internal/memo/service.go	86.20%	2 Missing and 2 partials ⚠️

📢 Thoughts on this report? Let us know!