docs: update model integration doc

packages/website/src/i18n/locales/en-US/docs.ts

@@ -115,32 +115,17 @@ export default {
 	model_integration: {
 		title: 'Model Integration',
 		subtitle:
-			'Supports OpenAI-compatible models with tool call support, including public cloud services and private deployments.',
+			'Supports models that comply with OpenAI API specification and support tool calls, including public cloud services and private deployments.',
+		recommendation_logic: 'Recommended: Lightweight models with strong ToolCall capabilities',
 		recommended: 'Recommended Models',
-		model_gpt4_title: '⚡ gpt-4.1-mini',
-		model_gpt4_badge: 'Evaluation Baseline ✅',
-		model_gpt4_1: '• Cost-effective',
-		model_gpt4_2: '• Fast',
-		model_gpt4_3: '• High success rate',
-		model_deepseek_title: '💰 DeepSeek-3.2',
-		model_deepseek_badge: 'Economical',
-		model_deepseek_1: '• Much cheaper than similar models',
-		model_deepseek_2: '• ToolCall may error but usually auto-recovers',
-		model_deepseek_3: "• This site's free demo uses DeepSeek",
-		model_qwen_title: '🛡️ qwen3',
-		model_qwen_badge: 'Secure & Compliant',
-		model_qwen_1: '• Controllable, decent results, reasonable price',
-		model_qwen_2: '• ToolCall may error but usually auto-recovers',
-		model_qwen_3: '• Best for scenarios with detailed steps',
-		model_gemini_title: '⚡ gemini-2.5-flash',
-		model_gemini_badge: 'Highly efficient, high success rate, reasonable price',
 		available: 'Available Models',
-		available_verified: '✅ Verified Working',
+		available_verified: 'Verified Working Models',
 		tips: 'Tips',
 		tip_1: 'Reasoning models (like GPT-5) are slower with no advantage',
 		tip_2:
-			"Non-OpenAI models don't guarantee JSON schema compliance—tool call may error but usually recovers. Higher temperature recommended",
-		tip_3: 'Small/nano models perform poorly',
+			'Models with weaker ToolCall capabilities may return incorrect formats. Common errors usually auto-recover. Higher temperature recommended',
+		tip_3:
+			'Small models or those unable to handle complex tool definitions typically perform poorly',
 		security: '🔐 Production Authentication',
 		security_warning: '⚠️ Never commit real LLM API Keys to your frontend codebase',
 		security_desc:

packages/website/src/i18n/locales/zh-CN/docs.ts

@@ -114,31 +114,15 @@ export default {
 	model_integration: {
 		title: '模型接入',
 		subtitle: '当前支持符合 OpenAI 接口规范且支持 tool call 的模型,包括公有云服务和私有部署方案。',
+		recommendation_logic: '推荐使用 ToolCall 能力强的轻量级模型',
 		recommended: '推荐模型',
-		model_gpt4_title: '⚡ gpt-4.1-mini',
-		model_gpt4_badge: '评估基准 ✅',
-		model_gpt4_1: '• 性价比高',
-		model_gpt4_2: '• 速度快',
-		model_gpt4_3: '• 成功率高',
-		model_deepseek_title: '💰 DeepSeek-3.2',
-		model_deepseek_badge: '经济实惠',
-		model_deepseek_1: '• 价格远低于同等级其他模型',
-		model_deepseek_2: '• ToolCall 有出错率,通常能够自动修复',
-		model_deepseek_3: '• 本网站提供的免费试用为 DeepSeek',
-		model_qwen_title: '🛡️ qwen3',
-		model_qwen_badge: '安全合规',
-		model_qwen_1: '• 可控、效果尚可,价格合理',
-		model_qwen_2: '• ToolCall 有出错率,通常能够自动修复',
-		model_qwen_3: '• 适合能给出详细步骤的场景',
-		model_gemini_title: '⚡ gemini-2.5-flash',
-		model_gemini_badge: '极其高效,成功率高,价格合理',
 		available: '可用模型',
-		available_verified: '✅ 已验证可用',
+		available_verified: '已验证可用模型',
 		tips: '提示',
 		tip_1: 'reasoning 模型(如 GPT-5),速度偏慢,没有必要',
 		tip_2:
-			'不保证 json schema 的模型(openAI 以外的几乎所有模型),tool call 有概率出错,通常能自动修复,建议 temperature 设置高一些',
-		tip_3: '小模型、nano 模型,效果不佳',
+			'ToolCall 能力较弱的模型可能返回错误的格式，常见错误能够自动恢复，建议设置较高的 temperature',
+		tip_3: '小模型或者无法适应复杂 Tool 定义的模型，通常效果不佳',
 		security: '🔐 生产环境鉴权建议',
 		security_warning: '⚠️ 永远不要把真实的 LLM API Key 发布到前端代码库',
 		security_desc: '在实际应用中,为了隐藏真实的 LLM API Key，建议采用以下架构:',