fix(phase6): make quantize_nbits optional so pre-Phase-6 workflows validate

quantize_nbits was added to the Core ML Converter node's required INPUT_TYPES,
so ComfyUI's /prompt validation rejected (HTTP 400) any workflow saved before
Phase 6 — the field is absent from those prompts. The Tier 2 golden-image test
caught this. Move it to optional: omitted inputs fall back to the convert()
default of "none", so old workflows validate and behave identically while new
users can still opt in. Restores the Gate 6 'existing workflows unaffected'
guarantee.

coreml_suite/nodes.py

@@ -247,12 +247,15 @@ class CoreMLConverter(COREML_NODE):
                     ],
                 ),
                 "controlnet_support": ("BOOLEAN", {"default": False}),
-                # Phase 6: k-means weight palettization. "none" keeps the
-                # pre-Phase-6 behavior and filename, so existing cached
-                # .mlpackages still resolve.
-                "quantize_nbits": (list(QUANT_NBITS_VALUES), {"default": "none"}),
             },
             "optional": {
+                # Phase 6: k-means weight palettization. Kept optional so
+                # workflows saved before Phase 6 still validate — ComfyUI
+                # rejects a prompt that omits any `required` input. When
+                # omitted it defaults to "none", identical to pre-Phase-6
+                # behavior and filename, so existing cached .mlpackages
+                # still resolve.
+                "quantize_nbits": (list(QUANT_NBITS_VALUES), {"default": "none"}),
                 "lora_params": ("LORA_PARAMS",),
             },
         }