perf: max_token count;feat: support resoner output;fix: member scroll (#3681)

* perf: supplement assistant empty response

* check array

* perf: max_token count

* feat: support resoner output

* member scroll

* update provider order

* i18n

packages/web/i18n/zh-Hant/account.json

@@ -48,10 +48,10 @@
   "model.output_price": "模型輸出價格",
   "model.output_price_tip": "語言模型輸出價格，如果配置了該項，則模型綜合價格會失效",
   "model.param_name": "參數名",
-  "model.request_auth": "自訂請求 Tokens",
+  "model.request_auth": "自訂請求 Key",
   "model.request_auth_tip": "向自訂請求地址發起請求時候，攜帶請求頭：Authorization: Bearer xxx 進行請求",
   "model.request_url": "自訂請求地址",
-  "model.request_url_tip": "如果填入該值，則會直接向該位址發起請求，不經過 OneAPI",
+  "model.request_url_tip": "如果填寫該值，則會直接向該地址發起請求，不經過 OneAPI。\n需要遵循 OpenAI 的 API格式，並填寫完整請求地址，例如：\n\nLLM: {{host}}/v1/chat/completions\n\nEmbedding: {{host}}/v1/embeddings\n\nSTT: {{host}}/v1/audio/transcriptions\n\nTTS: {{host}}/v1/audio/speech\n\nRerank: {{host}}/v1/rerank",
   "model.test_model": "模型測試",
   "model.tool_choice": "支援工具調用",
   "model.tool_choice_tag": "工具調用",

packages/web/i18n/zh-Hant/app.json

@@ -109,6 +109,7 @@
   "publish_channel": "發布通道",
   "publish_success": "發布成功",
   "question_guide_tip": "對話結束後，會為你產生 3 個引導性問題。",
+  "reasoning_response": "輸出思考",
   "saved_success": "保存成功！\n如需在外部使用該版本，請點擊“儲存並發布”",
   "search_app": "搜尋應用程式",
   "setting_app": "應用程式設定",

packages/web/i18n/zh-Hant/chat.json

@@ -2,6 +2,7 @@
   "AI_input_is_empty": "傳送至 AI 節點的內容為空",
   "Delete_all": "清除所有詞彙",
   "LLM_model_response_empty": "模型流程回應為空，請檢查模型流程輸出是否正常",
+  "ai_reasoning": "思考過程",
   "chat_history": "對話紀錄",
   "chat_input_guide_lexicon_is_empty": "尚未設定詞彙庫",
   "chat_test_app": "調試-{{name}}",