Keep image point multiplier regression meaningful

The image-count pricing regression was passing an override into a helper that ignored it, so the test exercised the one-image default while expecting the four-image total. This makes the fixture accept the same node data overrides as the lower-level image node factory without touching production pricing logic.

Constraint: Remote master already contains the UI change that hides unimplemented image toolbar actions.

Rejected: Change GenerationComposer point calculation | the failing evidence showed draft.imageCount was never set by the fixture.

Confidence: high

Scope-risk: narrow

Tested: npm run test:run -- src/components/__tests__/ImageInputNode.test.tsx src/app/api/generate/providers/__tests__/newapiwg.test.ts src/app/api/points/estimate/__tests__/route.test.ts src/components/__tests__/GenerationComposer.test.tsx src/store/execution/__tests__/generateVideoExecutor.test.ts

Tested: npm run build

Tested: git diff --check

src/components/__tests__/GenerationComposer.test.tsx

@@ -120,7 +120,7 @@ function imageNode(id: string, selected = false, data: Partial<NanoBananaNodeDat
   } as WorkflowNode;
 }
 
-function pricedImageNode(id: string, selected = false): WorkflowNode {
+function pricedImageNode(id: string, selected = false, data: Partial<NanoBananaNodeData> = {}): WorkflowNode {
   return imageNode(id, selected, {
     selectedModel: {
       provider: "newapiwg",
@@ -129,6 +129,7 @@ function pricedImageNode(id: string, selected = false): WorkflowNode {
       capabilities: ["text-to-image", "image-to-image"],
       pricing: { type: "per-run", amount: 2 },
     },
+    ...data,
   });
 }