perf(ai-sdk): embed query once across router fan-out + fold umlauts in intent/concept matching

Authority Router re-embedded the query per collection (6x); on dev the embed
endpoint (OVH) is remote so that was 6 round-trips = 7-12s per /retrieve. Embed
once, reuse via ctx across the concurrent per-collection searches.
DetectIntent + ConceptNorms now fold ae/oe/ue/ss so ASCII (Pruefe) and umlaut
(Pruefe) inputs both match.

ai-compliance-sdk/internal/ucca/legal_rag_client.go

@@ -105,7 +105,7 @@ func (c *LegalRAGClient) searchInternal(ctx context.Context, collection string,
 		}
 	}
 
-	embedding, err := c.generateEmbedding(ctx, query)
+	embedding, err := c.embedForQuery(ctx, query)
 	if err != nil {
 		return nil, fmt.Errorf("failed to generate embedding: %w", err)
 	}