- 根因: deepseek-v4-flash-vision-exp 为 thinking 模型, content=[thinking,text] 共享 max_tokens,默认1024被长思考吃光→仅thinking块无text块, stop_reason=max_tokens → resp.Content="" → no reply produced - 仅当 req.MaxTokens==0 套用默认(显式值不受影响); loop→agent→anthropic 传递链无截断 - 新增 anthropic_budget_test(默认发8192 + 长思考短text断言Content=text+thinking不泄漏) - build/vet/test绿+交叉编译