fix(ai-sdk): keyword precision — stop adjective/generic ghost components

Class D (generic keyword hygiene, GT-guarded). Two over-broad keyword->component
mappings produced ghost components:
- "kuehl"/"cool" -> Kuehlaggregat (C095) matched product variants
  ("Cool-Ausfuehrung") and outputs ("kuehle Glaeser"). Narrowed to cooling-UNIT
  terms (kuehlaggregat, kuehlanlage, kuehler, kaeltemaschine, chiller, rueckkuehl).
- "filter" -> Absauganlage/Oelnebelabscheider (C124) matched any filter
  (Laugen-/Wasser-/Oelfilter). Keep "filteranlage" only.

No pattern or GT test depends on these mappings (Kistenhub/Bremse use hand-crafted
inputs). UC-M now parses 6 plausible components (was 8 incl. the two ghosts).
Warewashing GT recall 82.4% and Kistenhub/Bremse pins unchanged.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

ai-compliance-sdk/internal/iace/gt_warewashing_test.go

@@ -103,6 +103,17 @@ func TestWarewashing_GTCoverage(t *testing.T) {
 		t.Fatalf("parse GT: %v", err)
 	}
 
+	{
+		res := ParseNarrative(warewashingNarrative, "Gewerbliche Untertisch-Geschirrspuelmaschine (vernetzt)")
+		var cn []string
+		for _, c := range res.Components {
+			if !c.Negated {
+				cn = append(cn, c.NameDE)
+			}
+		}
+		t.Logf("Parsed components: %v", cn)
+	}
+
 	hazards, mitigations, nPatterns := warewashingEngineOutput()
 	t.Logf("Engine: %d patterns kept (relevance+cyber filter) -> %d hazards", nPatterns, len(hazards))