fix: 回退 Grok 从 isOpenAIThinkingEnabled 的自动检测

Grok 推理模型（如 grok-4.20-reasoning）自动进行推理，不需要
thinking/enable_thinking 请求参数。发送这些参数虽大概率被忽略
（OpenAI SDK 透传 unknown keys），但属于不正确行为。

Co-Authored-By: deepseek-v4-pro[1m] <deepseek-ai@claude-code-best.win>

src/services/api/openai/requestBody.ts

@@ -23,13 +23,11 @@ export function isOpenAIThinkingEnabled(model: string): boolean {
   if (isEnvDefinedFalsy(process.env.OPENAI_ENABLE_THINKING)) return false
   // Explicit enable
   if (isEnvTruthy(process.env.OPENAI_ENABLE_THINKING)) return true
-  // Auto-detect from model name (DeepSeek, MiMo, and Grok models support thinking mode)
+  // Auto-detect from model name (DeepSeek and MiMo models support thinking mode).
+  // Grok is intentionally excluded — Grok reasoning models reason automatically
+  // and do NOT require thinking/enable_thinking request body parameters.
   const modelLower = model.toLowerCase()
-  return (
-    modelLower.includes('deepseek') ||
-    modelLower.includes('mimo') ||
-    modelLower.includes('grok')
-  )
+  return modelLower.includes('deepseek') || modelLower.includes('mimo')
 }
 
 /**