Given a hex value and a proposed claim about it, return whether the archive supports that claim, what is missing, what kind of source would be needed, and safe wording.

This is Colour Memory's anti-hallucination endpoint. It turns the absence of evidence into a forensic finding rather than a gap to be filled with invention.

A claim can only be "supported" or "partial" if a candidate is both a genuinely close colour match (low dE2000) AND has real word-level overlap with the claim, using whole-word matching against a stopword-filtered set. A nearby-but-different colour that merely shares a generic word can never produce false confidence.

Example: hex #4A535C + proposed_claim 'cyanosis in a death chamber' Returns: nearest archive support, whether the claim is supported, what is missing, what source type would be needed, and safe agent wording.