Function find_semantic_duplicates 

pub fn find_semantic_duplicates(
    index: &KnowledgeEmbeddingIndex,
    engine: &EmbeddingEngine,
    knowledge: &ProjectKnowledge,
    new_category: &str,
    new_key: &str,
    new_value: &str,
    threshold: f32,
    limit: usize,
) -> Vec<SimilarFact>

Embedding-based near-duplicate detection for remember. Mirrors the lexical find_cross_key_similar but scores cosine similarity, so paraphrases that share few tokens are still caught. Read-only against the pre-upsert index, so the incoming fact never matches itself. Returns advisory hits for the agent to resolve via judge — it never mutates or merges facts.