Bug: An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'

Start with the attached lights example and org.example.LightsExample, especially the failing call reported at LightsExample.java:86. Build it with mvn clean install, run the two described inputs, and compare the behavior with the MODEL_ID set to the listed models. Done means the second input turns the lights on without the tool_calls validation error.

Describe the bug
Got the following error using Semantic Kernel in Java with automatic function calling using 4o* OpenAI models: "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'".

To Reproduce
Steps to reproduce the behavior:

1. Unzip provided example, build it and execute it:

mvn clean install
export OPENAI_API_KEY=sk-...
java -jar target/lights-example-1.0-SNAPSHOT.jar

2. Enter two consecute inputs: "get the lights" and "turn them on"
3. See error

SLF4J(W): No SLF4J providers were found.
SLF4J(W): Defaulting to no-operation (NOP) logger implementation
SLF4J(W): See https://www.slf4j.org/codes.html#noProviders for further details.
User > get the lights
Getting lights
Assistant > Here are the current states of the lights:

1. **Table Lamp**: Off
2. **Porch Light**: Off
3. **Chandelier**: On
User > turn them on
Exception in thread "main" com.azure.core.exception.HttpResponseException: Status code 400, "{
  "error": {
    "message": "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_Mor7WOBzlb1Ao9ryIczup9mS, call_ejzgT6RAATaWBqmJbrzbzAMP",
    "type": "invalid_request_error",
    "param": "messages",
    "code": null
  }
}"
	at com.azure.core.implementation.http.rest.RestProxyBase.instantiateUnexpectedException(RestProxyBase.java:388)
	at com.azure.core.implementation.http.rest.AsyncRestProxy.lambda$ensureExpectedStatus$1(AsyncRestProxy.java:135)
	at reactor.core.publisher.FluxMapFuseable$MapFuseableSubscriber.onNext(FluxMapFuseable.java:113)
	at reactor.core.publisher.MonoUsing$MonoUsingSubscriber.onNext(MonoUsing.java:231)
	at reactor.core.publisher.FluxHandle$HandleSubscriber.onNext(FluxHandle.java:126)
	at reactor.core.publisher.FluxMap$MapConditionalSubscriber.onNext(FluxMap.java:224)
	at reactor.core.publisher.FluxDoFinally$DoFinallySubscriber.onNext(FluxDoFinally.java:113)
	at reactor.core.publisher.FluxHandleFuseable$HandleFuseableSubscriber.onNext(FluxHandleFuseable.java:191)
	at reactor.core.publisher.FluxContextWrite$ContextWriteSubscriber.onNext(FluxContextWrite.java:107)
	at reactor.core.publisher.Operators$MonoSubscriber.complete(Operators.java:1839)
	at reactor.core.publisher.MonoCollectList$MonoCollectListSubscriber.onComplete(MonoCollectList.java:129)
	at reactor.core.publisher.FluxPeek$PeekSubscriber.onComplete(FluxPeek.java:260)
	at reactor.core.publisher.FluxMap$MapSubscriber.onComplete(FluxMap.java:144)
	at reactor.netty.channel.FluxReceive.onInboundComplete(FluxReceive.java:415)
	at reactor.netty.channel.ChannelOperations.onInboundComplete(ChannelOperations.java:439)
	at reactor.netty.channel.ChannelOperations.terminate(ChannelOperations.java:493)
	at reactor.netty.http.client.HttpClientOperations.onInboundNext(HttpClientOperations.java:789)
	at reactor.netty.channel.ChannelOperationsHandler.channelRead(ChannelOperationsHandler.java:114)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420)
	at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412)
	at com.azure.core.http.netty.implementation.AzureSdkHandler.channelRead(AzureSdkHandler.java:224)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420)
	at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412)
	at io.netty.channel.CombinedChannelDuplexHandler$DelegatingChannelHandlerContext.fireChannelRead(CombinedChannelDuplexHandler.java:436)
	at io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346)
	at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318)
	at io.netty.channel.CombinedChannelDuplexHandler.channelRead(CombinedChannelDuplexHandler.java:251)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420)
	at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412)
	at io.netty.handler.ssl.SslHandler.unwrap(SslHandler.java:1475)
	at io.netty.handler.ssl.SslHandler.decodeNonJdkCompatible(SslHandler.java:1349)
	at io.netty.handler.ssl.SslHandler.decode(SslHandler.java:1389)
	at io.netty.handler.codec.ByteToMessageDecoder.decodeRemovalReentryProtection(ByteToMessageDecoder.java:530)
	at io.netty.handler.codec.ByteToMessageDecoder.callDecode(ByteToMessageDecoder.java:469)
	at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:290)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420)
	at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412)
	at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1407)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440)
	at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420)
	at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:918)
	at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166)
	at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788)
	at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724)
	at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650)
	at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562)
	at io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:994)
	at io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
	at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30)
	at java.base/java.lang.Thread.run(Thread.java:1583)
	Suppressed: java.lang.Exception: #block terminated with an error
		at reactor.core.publisher.BlockingSingleSubscriber.blockingGet(BlockingSingleSubscriber.java:100)
		at reactor.core.publisher.Mono.block(Mono.java:1742)
		at org.example.LightsExample.main(LightsExample.java:86)

Expected behavior
The lights should be turned on.

Platform

• OS: Mac M1
• IDE: IntelliJ Idea or command line
• Language: Java
• Source: Maven repository, version 1.3.0

Additional context
The problem seems to be reproduced with models 4o and 4o-mini, but not with "gpt-3.5-turbo-0125". Change constant MODEL_ID in class LightsExample to see the difference.lights-example.zip