feat: add OpenAI client for fallback support

Implements ModelClient interface with OpenAI SDK to support GPT models
as fallback when local inference is unavailable. Includes tests with
mocked OpenAI API responses.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/models/openai.ts

@@ -0,0 +1,54 @@
+import OpenAI from 'openai';
+import type { ChatRequest, ChatResponse, ModelClient } from './types.js';
+
+export interface OpenAIClientConfig {
+  apiKey?: string;
+  model: string;
+  maxTokens?: number;
+  baseURL?: string;
+}
+
+export class OpenAIClient implements ModelClient {
+  private client: OpenAI;
+  private model: string;
+  private defaultMaxTokens: number;
+
+  constructor(config: OpenAIClientConfig) {
+    this.client = new OpenAI({
+      apiKey: config.apiKey,
+      baseURL: config.baseURL,
+    });
+    this.model = config.model;
+    this.defaultMaxTokens = config.maxTokens ?? 4096;
+  }
+
+  async chat(request: ChatRequest): Promise<ChatResponse> {
+    const messages: OpenAI.ChatCompletionMessageParam[] = [];
+
+    if (request.system) {
+      messages.push({ role: 'system', content: request.system });
+    }
+
+    for (const msg of request.messages) {
+      messages.push({ role: msg.role, content: msg.content });
+    }
+
+    const response = await this.client.chat.completions.create({
+      model: this.model,
+      max_tokens: request.maxTokens ?? this.defaultMaxTokens,
+      messages,
+    });
+
+    const choice = response.choices[0];
+    const content = choice?.message?.content ?? '';
+
+    return {
+      content,
+      stopReason: choice?.finish_reason ?? 'stop',
+      usage: {
+        inputTokens: response.usage?.prompt_tokens ?? 0,
+        outputTokens: response.usage?.completion_tokens ?? 0,
+      },
+    };
+  }
+}