diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py
index b5d5328fb0..f30a8acf89 100644
--- a/studio/backend/core/inference/llama_cpp.py
+++ b/studio/backend/core/inference/llama_cpp.py
@@ -1042,6 +1042,10 @@ class LlamaCppBackend:
 
     @property
     def supports_tools(self) -> bool:
+        # DiffusionGemma serves via the visual runner, whose live per-step canvas
+        # frames are dropped by the agentic tool loop; never route it through tools.
+        if self._is_diffusion:
+            return False
         return self._supports_tools
 
     @property
diff --git a/studio/frontend/src/components/assistant-ui/markdown-text.tsx b/studio/frontend/src/components/assistant-ui/markdown-text.tsx
index 02418753fa..8f91b419d2 100644
--- a/studio/frontend/src/components/assistant-ui/markdown-text.tsx
+++ b/studio/frontend/src/components/assistant-ui/markdown-text.tsx
@@ -286,11 +286,14 @@ function CodeBlockActions({
 }
 
 // DiffusionGemma renders its denoising live in the bubble (see DiffusionCanvas in
-// thread.tsx), so it no longer forces HTML into an iframe artifact; it follows the
-// same artifact rules as every other model.
+// thread.tsx) and has the artifacts canvas on by default, so a full-HTML answer
+// (e.g. a playable game) renders as an interactive card without the global toggle.
 function StreamdownBlock(props: BlockProps) {
   const shouldCollapseHtmlArtifacts = useChatRuntimeStore(
-    (state) => state.artifactsEnabled || state.collapseHtmlArtifacts,
+    (state) =>
+      state.artifactsEnabled ||
+      state.collapseHtmlArtifacts ||
+      state.loadedIsDiffusion,
   );
   const messageHasRenderableRenderHtmlTool = useAuiState(({ message }) =>
     message.parts.some(isRenderableRenderHtmlToolPart),