chore: update allium spec for clearer wording towards embedding model

specs/embedding.allium

@@ -213,6 +213,14 @@ invariant VectorCacheInDb {
     -- Enables instant reload without re-embedding
 }
 
+invariant RealNeuralModel {
+    -- Embeddings MUST be produced by the actual ONNX neural model (multilingual-e5-small),
+    -- not by lexical approximations (TF-IDF, bag-of-words, hash projections).
+    -- Cross-language semantic similarity is a primary requirement:
+    -- posts in different languages about the same topic must produce similar vectors.
+    -- This is only achievable with the trained multilingual transformer model.
+}
+
 invariant ModelCaching {
     -- Model files (~100 MB) downloaded from Hugging Face Hub on first use
     -- Cached in app data directory, persists across sessions