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/inception.ts

@@ -0,0 +1,42 @@
+import { createOpenAI } from '@ai-sdk/openai';
+import { GatewayFetchError } from '~~/server/utils/ai-provider';
+import { Err, Ok } from '~~/types/result';
+import type { ProviderModule } from '.';
+
+export default {
+    id: 'inception',
+    baseUrl: 'https://api.inceptionlabs.ai/v1',
+    modelsEndpoint: null,
+
+    createGateway({ apiKey, baseURL }) {
+        if (apiKey === undefined) {
+            return Err(GatewayFetchError.NoProviderApiKey);
+        }
+
+        return Ok({
+            gateway: createOpenAI({ name: 'Inception', apiKey, baseURL }),
+            streamTransformer: undefined,
+            textTransformer: undefined,
+        });
+    },
+
+    getAuthHeaders(apiKey) {
+        return apiKey ? { Authorization: `Bearer ${apiKey}` } : {};
+    },
+
+    async fetchModels() {
+        // inception doesn't have a model list endpoint so we hardcode them
+        return [
+            {
+                id: "mercury-2",
+                name: "Mercury 2",
+                attributes: {
+                    inputModalities: ['text'],
+                    outputModalities: ['text'],
+                    capabilities: ['tools', 'reasoning'],
+                    contextWindow: 128_000,
+                }
+            },
+        ];
+    },
+} satisfies ProviderModule;