fix(model): anthropic默认max_tokens 1024→8192 — thinking+text共享预算,长思考不再截断正文为空

- 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

internal/runtime/model/anthropic.go

@@ -20,7 +20,8 @@ const (
 	// anthropicDefaultMaxTokens is the default max_tokens sent when
 	// Request.MaxTokens is zero. Anthropic requires max_tokens to be present and
 	// positive, so a sensible default is applied rather than omitting it.
-	anthropicDefaultMaxTokens = 1024
+	// max_tokens is shared by thinking + text, so it must leave room for both.
+	anthropicDefaultMaxTokens = 8192
 	// anthropicDataPrefix marks a payload embedded as a data: URI.
 	anthropicDataPrefix = "data:"
 )