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/en/account.json

@@ -49,10 +49,10 @@
   "model.output_price": "Output price",
   "model.output_price_tip": "The language model output price. If this item is configured, the model comprehensive price will be invalid.",
   "model.param_name": "Parameter name",
-  "model.request_auth": "Custom token",
+  "model.request_auth": "Custom key",
   "model.request_auth_tip": "When making a request to a custom request address, carry the request header: Authorization: Bearer xxx to make the request.",
   "model.request_url": "Custom url",
-  "model.request_url_tip": "If this value is filled in, a request will be made directly to this address without going through OneAPI",
+  "model.request_url_tip": "If you fill in this value, you will initiate a request directly without passing. \nYou need to follow the API format of Openai and fill in the full request address, such as\n\nLLM: {Host}}/v1/Chat/Completions\n\nEmbedding: {host}}/v1/embeddings\n\nSTT: {Host}/v1/Audio/Transcriptions\n\nTTS: {Host}}/v1/Audio/Speech\n\nRERARARARARARARANK: {Host}}/v1/RERARARARARARARARARARANK",
   "model.test_model": "Model testing",
   "model.tool_choice": "Tool choice",
   "model.tool_choice_tag": "ToolCall",

packages/web/i18n/en/app.json

@@ -109,6 +109,7 @@
   "publish_channel": "Publish",
   "publish_success": "Publish Successful",
   "question_guide_tip": "After the conversation, 3 guiding questions will be generated for you.",
+  "reasoning_response": "Output thinking",
   "saved_success": "Saved successfully! \nTo use this version externally, click Save and Publish",
   "search_app": "Search apps",
   "setting_app": "Workflow",

packages/web/i18n/en/chat.json

@@ -2,6 +2,7 @@
   "AI_input_is_empty": "The content passed to the AI ​​node is empty",
   "Delete_all": "Clear All Lexicon",
   "LLM_model_response_empty": "The model flow response is empty, please check whether the model flow output is normal.",
+  "ai_reasoning": "Thinking process",
   "chat_history": "Conversation History",
   "chat_input_guide_lexicon_is_empty": "Lexicon not configured yet",
   "chat_test_app": "Debug-{{name}}",

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

@@ -49,10 +49,10 @@
   "model.output_price": "模型输出价格",
   "model.output_price_tip": "语言模型输出价格，如果配置了该项，则模型综合价格会失效",
   "model.param_name": "参数名",
-  "model.request_auth": "自定义请求 Tokens",
+  "model.request_auth": "自定义请求 Key",
   "model.request_auth_tip": "向自定义请求地址发起请求时候，携带请求头：Authorization: Bearer xxx 进行请求",
   "model.request_url": "自定义请求地址",
-  "model.request_url_tip": "如果填写该值，则会直接向该地址发起请求，不经过 OneAPI",
+  "model.request_url_tip": "如果填写该值，则会直接向该地址发起请求，不经过 OneAPI。需要遵循 OpenAI 的 API格式，并填写完整请求地址，例如：\nLLM: {{host}}/v1/chat/completions\nEmbedding: {{host}}/v1/embeddings\nSTT: {{host}}/v1/audio/transcriptions\nTTS: {{host}}/v1/audio/speech\nRerank: {{host}}/v1/rerank",
   "model.test_model": "模型测试",
   "model.tool_choice": "支持工具调用",
   "model.tool_choice_tag": "工具调用",

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

@@ -109,6 +109,7 @@
   "publish_channel": "发布渠道",
   "publish_success": "发布成功",
   "question_guide_tip": "对话结束后，会为你生成 3 个引导性问题。",
+  "reasoning_response": "输出思考",
   "saved_success": "保存成功！如需在外部使用该版本，请点击“保存并发布”",
   "search_app": "搜索应用",
   "setting_app": "应用配置",

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

@@ -2,6 +2,7 @@
   "AI_input_is_empty": "传入AI 节点的内容为空",
   "Delete_all": "清空词库",
   "LLM_model_response_empty": "模型流响应为空，请检查模型流输出是否正常",
+  "ai_reasoning": "思考过程",
   "chat_history": "聊天记录",
   "chat_input_guide_lexicon_is_empty": "还没有配置词库",
   "chat_test_app": "调试-{{name}}",

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}}",