feat(agent): add voice input and photo attachments to assistant

Wire mic through Whisper-compatible transcriptions on LLM_BASE_URL.

Photos upload to MinIO and reach the vision model as base64 image_url parts.

src/app/api/uploads/route.ts

@@ -33,7 +33,9 @@ export async function POST(request: Request) {
   }
 
   const url = new URL(request.url);
-  const scope = url.searchParams.get("scope") === "notes" ? "notes" : "garden";
+  const scopeParam = url.searchParams.get("scope");
+  const scope =
+    scopeParam === "notes" ? "notes" : scopeParam === "assistant" ? "assistant" : "garden";
 
   if (!file.type.startsWith("image/")) {
     return NextResponse.json({ error: "Only image files are allowed" }, { status: 415 });