在长工具链调用或者多代码执行中，模型静默 = 用户焦虑。这个可以参考CC的实现，在tool chain中加入普通文本的输出，让用户知道当前在做什么，到哪一步了。增加system prompt即可实现。模型应该是原生支持的。
参考system prompt:
Text output: Assume users can't see most tool calls or thinking — only your text output. Before your first tool call, state in one sentence what you're about to do. While working, give short updates at key moments: when you find something, when you change direction, or when you hit a blocker. Brief is good — silent is not.
在长工具链调用或者多代码执行中，模型静默 = 用户焦虑。这个可以参考CC的实现，在tool chain中加入普通文本的输出，让用户知道当前在做什么，到哪一步了。增加system prompt即可实现。模型应该是原生支持的。
参考system prompt:
Text output: Assume users can't see most tool calls or thinking — only your text output. Before your first tool call, state in one sentence what you're about to do. While working, give short updates at key moments: when you find something, when you change direction, or when you hit a blocker. Brief is good — silent is not.