+ {isZh + ? '并非所有模型都能正确处理 page-agent 的 tool 定义。请查看' + : 'Not all models can handle page-agent tool definitions correctly. Check the '} + + {isZh ? '已测试模型列表' : 'tested models list'} + + {isZh ? '。' : '.'} +
+
+ {isZh
+ ? '如果使用了 API 代理或网关，请确保请求中的 '
+ : 'If using an API proxy or gateway, make sure the '}
+ tools
+ {isZh
+ ? ' 字段被完整、无修改地转发给模型供应商。部分代理可能会剥离或修改此字段。'
+ : ' parameter is forwarded to the model provider intact. Some proxies may strip or alter this field.'}
+
+ {isZh ? ( + <> + 如果以上步骤无法解决问题，欢迎在{' '} + + GitHub Discussions + {' '} + 中反馈，附上模型名称和错误信息。 + + ) : ( + <> + If the above steps don't help, join the{' '} + + GitHub Discussions + {' '} + with your model name and error details. + + )} +
++ {isZh + ? '按以下顺序逐步排查，从最简单的情况开始：' + : 'Follow this diagnostic funnel from simplest to most advanced:'} +
++ {isZh + ? '给一个具体的、单步的简单指令（如"点击登录按钮"），看 Agent 能否完成。如果连简单操作都失败了，问题可能不在模型能力上。' + : 'Give a concrete, single-step instruction (e.g. "click the login button"). If even simple actions fail, the issue is likely not model capability.'} +
++ {isZh + ? '切换到你能获取到的最先进、最大的模型，以排除是否是模型智能水平不足导致的问题。' + : "Switch to the most capable model you have access to, to isolate whether it's a model intelligence issue."} +
++ {isZh + ? '给出尽可能具体的指令。对于复杂任务，建议使用另一个 LLM 来预先拆分和细化用户的需求，然后逐步执行。' + : "Be as specific as possible. For complex tasks, consider using another LLM to decompose and refine the user's request before execution."} +
++ {isZh + ? '通过 instructions 配置注入网站背景描述、关键术语解释等上下文信息，帮助 Agent 更好地理解页面。' + : 'Use the instructions config to inject website descriptions, key terminology, and background context to help the agent understand the page.'} +
++ {isZh + ? '使用开发者工具检查清洗后的 HTML，确认关键信息、文本和可操作元素是否被正确保留。' + : 'Inspect the sanitized HTML in dev tools to confirm that key information, text, and interactive elements are preserved correctly.'} +
++ {isZh + ? '并非所有网站都提供了完善的语义化 HTML 和 accessibility 标签。对于此类网站，DOM 清洗可能无法产出足够好的结果。' + : 'Not all websites provide proper semantic HTML and accessibility labels. For such sites, DOM sanitization may not produce good enough results.'} +
++ {isZh + ? '确认目标元素是否为图片、Canvas、或需要复杂交互（如拖拽、基于坐标的点击）的元素。这些本身就超出了当前的能力范围。' + : 'Verify if the target is an image, Canvas, or requires complex interactions (drag-and-drop, coordinate-based clicking). These are beyond current capabilities.'} +
++ {isZh + ? '检查清洗结果中是否存在关键信息丢失、可操作元素未被编号等问题。' + : 'Look for missing key information or unnumbered interactive elements in the sanitized output.'} +
++ {isZh + ? '通过注入脚本为网站添加 aria-label、语义化标签等 accessibility 属性，改善 DOM 清洗质量。' + : 'Inject scripts to add aria-labels, semantic attributes, and other a11y improvements to enhance DOM sanitization quality.'} +
++ {isZh ? ( + <> + 对于特定的、持续难以操作的元素，考虑开发{' '} + + 自定义 Tool + {' '} + 来直接操作这些元素。 + + ) : ( + <> + For consistently difficult elements, consider building a{' '} + + custom Tool + {' '} + to interact with them directly. + + )} +
++ {isZh + ? '一些 LLM 供应商使用了与 OpenAI 不完全兼容的参数格式，导致请求参数校验失败。' + : 'Some LLM providers use parameter formats that are not fully compatible with the OpenAI spec, causing request validation failures.'} +
++ {isZh ? '解决方案：使用 customFetch' : 'Solution: use customFetch'} +
++ {isZh + ? '通过 customFetch 配置拦截请求，在发送前调整参数格式以适配目标供应商的要求。' + : 'Use the customFetch config to intercept requests and adapt parameters before sending them to the target provider.'} +
++ {isZh ? '参见 ' : 'See '} + + PageAgentCore API + + {isZh ? ' 了解 customFetch 的完整用法。' : ' for full customFetch documentation.'} +
++ {isZh + ? '遇到问题了？按症状查找解决方案。' + : 'Running into issues? Find solutions by symptom.'} +
*/} +{isZh ? section.symptom.zh : section.symptom.en}
+