Semantic-search MCPs can turn tool output into a surprisingly fat state log. Before handing that accumulated diary to Jev, I’d put a deterministic Tier-1 compaction boundary in front of serialization: retain active files/symbols, constraints, and evidence pointers; drop repeated prose. That keeps Jev focused on decision inputs and makes token cost visible. contextpress looks designed for that preflight: https://github.com/Taha-azizi/contextpress and https://pypi.org/project/contextpress/