feat: add reasoning_effort configuration support for Doubao/GPT-5 models (#947)

* feat: Add reasoning effort configuration support

* Add `reasoning_effort` parameter to model config and agent initialization
* Support reasoning effort levels (minimal/low/medium/high) for Doubao/GPT-5 models
* Add UI controls in input box for reasoning effort selection
* Update doubao-seed-1.8 example config with reasoning effort support

Fixes & Cleanup:
* Ensure UTF-8 encoding for file operations
* Remove unused imports

* fix: set reasoning_effort to None for unsupported models

* fix: unit test error

* Update frontend/src/components/workspace/input-box.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

frontend/src/core/i18n/locales/zh-CN.ts

@@ -80,6 +80,15 @@ export const zhCN: Translations = {
     ultraMode: "Ultra",
     ultraModeDescription:
       "继承自 Pro 模式，可调用子代理分工协作，适合复杂多步骤任务，能力最强",
+    reasoningEffort: "推理深度",
+    reasoningEffortMinimal: "最低",
+    reasoningEffortMinimalDescription: "检索 + 直接输出",
+    reasoningEffortLow: "低",
+    reasoningEffortLowDescription: "简单逻辑校验 + 浅层推演",
+    reasoningEffortMedium: "中",
+    reasoningEffortMediumDescription: "多层逻辑分析 + 基础验证",
+    reasoningEffortHigh: "高",
+    reasoningEffortHighDescription: "全维度逻辑推演 + 多路径验证 + 反推校验",
     searchModels: "搜索模型...",
     surpriseMe: "小惊喜",
     surpriseMePrompt: "给我一个小惊喜吧",