ollama+mcp不能流返回

1、配置文件
spring:
ai:
openai:
base-url: http://192.168.1.123:11434
chat:
options:
model: qwen2.5:7b-instruct-fp16
stream-usage: true

mcp:
  client:
    type: async
    sse:
      connections:
        mcp-server-chart:
          url: http://localhost:1122/

2、代码
@Primary
@Bean
public ChatClient chatClient(ChatClient.Builder builder, ChatMemory chatMemory, ToolCallbackProvider tools) {
return builder.defaultSystem("""
你是一个智能人工助手
""")
.defaultAdvisors(
MessageChatMemoryAdvisor.builder(chatMemory).build(),
new SimpleLoggerAdvisor(
ModelOptionsUtils::toJsonStringPrettyPrinter,
ModelOptionsUtils::toJsonStringPrettyPrinter,
0
)
)
.defaultToolCallbacks(tools)
.build();
}

如果注释调.defaultToolCallbacks(tools) 这个。 就可以流返回。 如果加上后。AI回复的结果就变成了一次全返回

Start with the ChatClient bean in the issue, comparing the streaming behavior with and without .defaultToolCallbacks(tools). Reproduce the configuration using Ollama and the MCP SSE connection; done means AI responses remain incrementally streamed while MCP tools are enabled.