feat: add FastAPI model/load endpoint and all Next.js proxy routes (tasks 2-4)

src/app/api/model/load/route.ts

@@ -0,0 +1,37 @@
+import { NextRequest, NextResponse } from 'next/server';
+
+const INFERENCE_API_URL = process.env.INFERENCE_API_URL || 'http://localhost:8001';
+const INFERENCE_API_TIMEOUT = parseInt(process.env.INFERENCE_API_TIMEOUT || '30000', 10);
+
+export async function POST(request: NextRequest) {
+  const controller = new AbortController();
+  const timeoutId = setTimeout(() => controller.abort(), INFERENCE_API_TIMEOUT);
+
+  try {
+    const body = await request.json();
+
+    const response = await fetch(`${INFERENCE_API_URL}/model/load`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify(body),
+      signal: controller.signal,
+    });
+    clearTimeout(timeoutId);
+
+    const data = await response.json();
+    if (!response.ok) {
+      return NextResponse.json({ error: data.detail || 'Failed to load model' }, { status: response.status });
+    }
+    return NextResponse.json(data);
+  } catch (error: any) {
+    clearTimeout(timeoutId);
+    if (error.name === 'AbortError') {
+      return NextResponse.json({ error: 'Model load timed out' }, { status: 504 });
+    }
+    if (error.cause?.code === 'ECONNREFUSED' || error.message?.includes('fetch failed')) {
+      return NextResponse.json({ error: 'Inference service unavailable' }, { status: 503 });
+    }
+    console.error('model/load proxy error:', error);
+    return NextResponse.json({ error: 'Internal server error' }, { status: 500 });
+  }
+}