Please confirm if it is a bug,Springai encountered an error while calling VLLM

Bug description
Springai encountered an error while calling VLLM

org.springframework.ai.retry.NonTransientAiException: HTTP 400 - {"object":"error","message":"[{'type': 'missing', 'loc': ('body',), 'msg': 'Field required', 'input': None}]","type":"Bad Request","param":null,"code":400}

Environment
vllm version 0.9.2
spring-ai-starter-model-openai 1.0.0

spring.ai.openai.api-key=test
spring.ai.openai.base-url=http://xxx:8000
spring.ai.openai.chat.options.model=Qwen1.5-1.8B-Chat

Minimal Complete Reproducible example
@GetMapping("/ai/generate")
public Map<String,String> generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
System.out.printf("Generating a message for %s\n", message);
return Map.of("generation", this.chatModel.call(message));
}

Start with the minimal /ai/generate example and reproduce the call using Spring AI 1.0.0, vLLM 0.9.2, and the configured base URL and model. Compare the request with the reported HTTP 400 response, then determine whether this is a Spring AI compatibility bug, a vLLM API mismatch, or configuration; done means the cause and ownership are confirmed.