refactor: extract provider logic into modular registry

Each AI provider now has its own module implementing a ProviderModule
interface with createGateway, getAuthHeaders, and fetchModels methods.
This replaces the monolithic switch statements in ai-provider.ts and
models.post.ts with a clean registry pattern.

server/utils/providers/cerebras.ts

@@ -0,0 +1,44 @@
+import { createCerebras } from '@ai-sdk/cerebras';
+import { GatewayFetchError } from '~~/server/utils/ai-provider';
+import { Err, Ok } from '~~/types/result';
+import type { ProviderModule } from '.';
+import { getModelData } from './helpers';
+
+export default {
+    id: 'cerebras',
+    baseUrl: 'https://api.cerebras.ai/v1',
+    modelsEndpoint: '/models',
+
+    createGateway({ apiKey, baseURL }) {
+        if (apiKey === undefined) {
+            return Err(GatewayFetchError.NoProviderApiKey);
+        }
+
+        return Ok({
+            gateway: createCerebras({ apiKey, baseURL }),
+            streamTransformer: undefined,
+            textTransformer: undefined,
+        });
+    },
+
+    getAuthHeaders(apiKey) {
+        return apiKey ? { Authorization: `Bearer ${apiKey}` } : {};
+    },
+
+    async fetchModels({ baseURL, apiKey, modelsDevData }) {
+        const res = await fetch(`${baseURL}/models`, {
+            method: 'GET',
+            headers: { Authorization: `Bearer ${apiKey}` },
+        });
+        const data = await res.json();
+
+        if (!res.ok) {
+            throw createError({ statusCode: res.status, message: JSON.stringify(data) });
+        }
+
+        return data.data.map((model: any) => ({
+            ...getModelData(model.id, 'cerebras', modelsDevData),
+            id: model.id,
+        }));
+    },
+} satisfies ProviderModule;