feat(codex-image): 封装 GPT Image 2 图片接口并收紧错误处理

- 新增 openai:image 路由、planner 与 finalize，内部通过 Codex responses image_generation tool 执行生图

- 补充 Codex OAuth/header 兼容、图片 success report 本地处理与相关前后端/集成测试

- 禁止 chat/completions 使用 gpt-image-2，图片接口限制 n=1，并移除 Provider 模型页的图片能力开关

frontend/src/mocks/data.ts

@@ -878,6 +878,7 @@ export const MOCK_API_FORMATS = {
     { value: 'claude:cli', label: 'Claude CLI', default_path: '/v1/messages', aliases: [] },
     { value: 'openai:chat', label: 'OpenAI Chat', default_path: '/v1/chat/completions', aliases: [] },
     { value: 'openai:cli', label: 'OpenAI CLI', default_path: '/v1/responses', aliases: [] },
+    { value: 'openai:image', label: 'OpenAI Image', default_path: '/v1/images/generations', aliases: [] },
     { value: 'openai:video', label: 'OpenAI Video', default_path: '/v1/videos', aliases: [] },
     { value: 'gemini:chat', label: 'Gemini Chat', default_path: '/v1beta/models/{model}:{action}', aliases: [] },
     { value: 'gemini:cli', label: 'Gemini CLI', default_path: '/v1beta/models/{model}:{action}', aliases: [] },