feat(ollama): enhance model pull with improved error handling, persistence, and UI

- Add catalog metadata lookup for better error messages with hints (e.g., for missing manifests or tags)
- Persist downloaded model references in saved remote models for future reuse
- Replace searchRemoteModels import with getSavedRemoteModels in search route
- Enhance pull progress UI to display download bytes, digest, and fallback message when data is unavailable
- Improve error payload with model details, URL, and tags count to guide users toward valid tags or models

app/api/ollama/search/route.ts

@@ -1,17 +1,27 @@
 import { NextRequest, NextResponse } from "next/server";
-import { searchRemoteModels } from "@/lib/ollama";
+import { getSavedRemoteModels } from "@/lib/user-remote-models";
 
 export async function GET(request: NextRequest) {
   try {
     const { searchParams } = new URL(request.url);
     const query = searchParams.get("q") || undefined;
 
-    const remoteModels = await searchRemoteModels(query);
+    const saved = await getSavedRemoteModels();
+    const q = (query || "").trim().toLowerCase();
+    const filtered = q
+      ? saved.filter((m) => m.name.toLowerCase().includes(q))
+      : saved;
 
-    return NextResponse.json({
-      success: true,
-      models: remoteModels,
-    });
+    const models = filtered.map((m) => ({
+      name: m.name,
+      description: m.description,
+      url: m.url,
+      tags_count: m.tags_count,
+      installed: m.installed === true,
+      remote: true,
+    }));
+
+    return NextResponse.json({ success: true, models });
   } catch (error) {
     console.error("Error searching remote models:", error);
     return NextResponse.json(