fix(deepseek): back-fill reasoning_content for all assistant turns

channel/web/static/js/console.js

@@ -38,7 +38,7 @@ const I18N = {
         config_max_tokens: '最大上下文 Token', config_max_tokens_hint: '对话中 Agent 能输入的最大 Token 长度，超过后会智能压缩处理',
         config_max_turns: '最大记忆轮次', config_max_turns_hint: '一问一答为一轮，超过后会智能压缩处理',
         config_max_steps: '最大执行步数', config_max_steps_hint: '单次对话中 Agent 最多调用工具的次数',
-        config_enable_thinking: '深度思考', config_enable_thinking_hint: '开启后模型启用思考模式，回答质量更高但首字延迟增加，Web 端可展示思考过程',
+        config_enable_thinking: '深度思考', config_enable_thinking_hint: '是否启用深度思考模式',
         config_channel_type: '通道类型',
         config_provider: '模型厂商', config_model_name: '模型',
         config_custom_model_hint: '输入自定义模型名称',
@@ -124,7 +124,7 @@ const I18N = {
         config_max_tokens: 'Max Context Tokens', config_max_tokens_hint: 'Max tokens the Agent can input per conversation, auto-compressed when exceeded',
         config_max_turns: 'Max Memory Turns', config_max_turns_hint: 'One Q&A pair = one turn, auto-compressed when exceeded',
         config_max_steps: 'Max Steps', config_max_steps_hint: 'Max tool calls the Agent can make in a single conversation',
-        config_enable_thinking: 'Deep Thinking', config_enable_thinking_hint: 'Model reasons before answering for higher quality at the cost of first-token latency. Web console shows the reasoning trace.',
+        config_enable_thinking: 'Deep Thinking', config_enable_thinking_hint: 'Enable deep thinking mode',
         config_channel_type: 'Channel Type',
         config_provider: 'Provider', config_model_name: 'Model',
         config_custom_model_hint: 'Enter custom model name',