Fix flakey conversation flow test

[gt-oai]

I've seen this test fail with:

 - Mock #1.
        	Expected range of matching incoming requests: == 2
        	Number of matched incoming requests: 1

This is because we pop the wrong task_complete events and then the test exits. I think this is because the MCP events are now buffered after #8874.

So:

1. clear the buffer before we do any user message sending
2. additionally listen for task start before task complete
3. use the ID from task start to find the correct task complete event.