fix: allow consumption of entire response body for large payloads

[ewong5]

Motivation and Context

See this issue: #470

How Has This Been Tested?

Tested using the test classes provided and locally trying E2E

Breaking Changes

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

[rsg-coder]

This issue is still reproducible with this fix.

Setup
MCP Server is Python (FastMcp 2.9) which is hosting a calculator tool.
Client is a Java client using SSE to connect to the server and calling tools in a loop
Took the code changes of the above commit

Client Code
`

static void execTools(McpSyncClient client, List<McpSchema.Tool> tools) {

    var toolCallResult1 = client.callTool(McpSchema.CallToolRequest.builder().name("multiply_two_numbers").arguments(Map.of("n1", 12, "n2", 49)).build());
    System.out.println(toolCallResult1.content());

    var toolCallResult2 = client.callTool(McpSchema.CallToolRequest.builder().name("divide_two_numbers").arguments(Map.of("n1", 12, "n2", 49)).build());
    System.out.println(toolCallResult2.content());

    var toolCallResult3 = client.callTool(McpSchema.CallToolRequest.builder().name("add_two_numbers").arguments(Map.of("n1", 12, "n2", 49)).build());
    System.out.println(toolCallResult3.content());

    var toolCallResult4 = client.callTool(McpSchema.CallToolRequest.builder().name("subtract_two_numbers").arguments(Map.of("n1", 12, "n2", 49)).build());
    System.out.println(toolCallResult4.content());



}

`

Error
The error happens after 14-15 iterations of these calls.

`
22:11:56.374 [main] DEBUG i.m.spec.McpClientSession - Sending message for method tools/call
Exception in thread "main" reactor.core.Exceptions$ReactiveException: java.util.concurrent.TimeoutException: Did not observe any item or terminal signal within 10000ms in 'source(MonoDeferContextual)' (and no fallback has been configured)
at reactor.core.Exceptions.propagate(Exceptions.java:410)
at reactor.core.publisher.BlockingSingleSubscriber.blockingGet(BlockingSingleSubscriber.java:102)
at reactor.core.publisher.Mono.block(Mono.java:1779)
at io.modelcontextprotocol.client.McpSyncClient.callTool(McpSyncClient.java:227)
at agentic.mcp.StandardMcpClient.execTools(StandardMcpClient.java:131)
at agentic.mcp.StandardMcpClient.lambda$main$2(StandardMcpClient.java:107)
at java.base/java.util.stream.Streams$RangeIntSpliterator.forEachRemaining(Streams.java:104)
at java.base/java.util.stream.IntPipeline$Head.forEach(IntPipeline.java:617)
at agentic.mcp.StandardMcpClient.main(StandardMcpClient.java:99)
Suppressed: java.lang.Exception: #block terminated with an error
at reactor.core.publisher.BlockingSingleSubscriber.blockingGet(BlockingSingleSubscriber.java:104)
... 7 more
Caused by: java.util.concurrent.TimeoutException: Did not observe any item or terminal signal within 10000ms in 'source(MonoDeferContextual)' (and no fallback has been configured)
at reactor.core.publisher.FluxTimeout$TimeoutMainSubscriber.handleTimeout(FluxTimeout.java:296)
at reactor.core.publisher.FluxTimeout$TimeoutMainSubscriber.doTimeout(FluxTimeout.java:281)
at reactor.core.publisher.FluxTimeout$TimeoutTimeoutSubscriber.onNext(FluxTimeout.java:420)
at reactor.core.publisher.FluxOnErrorReturn$ReturnSubscriber.onNext(FluxOnErrorReturn.java:162)
at reactor.core.publisher.MonoDelay$MonoDelayRunnable.propagateDelay(MonoDelay.java:270)
at reactor.core.publisher.MonoDelay$MonoDelayRunnable.run(MonoDelay.java:285)
at reactor.core.scheduler.SchedulerTask.call(SchedulerTask.java:68)
at reactor.core.scheduler.SchedulerTask.call(SchedulerTask.java:28)
at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:317)
at java.base/java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:304)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1144)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
at java.base/java.lang.Thread.run(Thread.java:1583)

`

On the python side, I am getting errors that the resource is closed anyio.ClosedResourceError
Verified with another mcp client which works without errors on both client and server
Please let me know if I am missing something.

Thanks in advance.

-Ravi

[rsg-coder]

One more observation, as an addition to my previous comment.
This issue is reproducible with 0.11.2 + the changes of this commit.

With the latest build of main + the changes of this commit + changes of #502, the client is very stable and I have not had any issue across multiple repeated tests.