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/en-US.ts

@@ -82,6 +82,15 @@ export const enUS: Translations = {
     ultraMode: "Ultra",
     ultraModeDescription:
       "Pro mode with subagents to divide work; best for complex multi-step tasks",
+    reasoningEffort: "Reasoning Effort",
+    reasoningEffortMinimal: "Minimal",
+    reasoningEffortMinimalDescription: "Retrieval + Direct Output",
+    reasoningEffortLow: "Low",
+    reasoningEffortLowDescription: "Simple Logic Check + Shallow Deduction",
+    reasoningEffortMedium: "Medium",
+    reasoningEffortMediumDescription: "Multi-layer Logic Analysis + Basic Verification",
+    reasoningEffortHigh: "High",
+    reasoningEffortHighDescription: "Full-dimensional Logic Deduction + Multi-path Verification + Backward Check",
     searchModels: "Search models...",
     surpriseMe: "Surprise",
     surpriseMePrompt: "Surprise me",