>The constraint for the bank comes when you start spending that money. Most people take loans to spend the money, eg a company might invest in some new machinery or you might buy a house. The Mr Wagner in your story stopped his investigation too early.
No, you don't get it. Imagine if there was a single bank and no cash withdrawals. The bank can't run out of liquidity, ever. If you buy something from a company, the money lands in the bank account of the company, which is managed by the same bank. This means as long as there is no cross bank transfer, there is no limit to how much money can be created.
Now you might argue that this is a bit unrealistic, but at least in principle you could artificially engineer a situation like that even in the current system by having large corporations agree to use the same bank for money created by a specific loan.
But here is where it gets weirder. Imagine if there are two banks now. Surely now the idea presented above breaks down the moment there is a cross bank transfer, right? Except it's not that simple. There is merely a limit to how much of the created money can leave the bank in one direction. If the cross bank transfers are balanced so that for every transfer from bank one to bank two, there is a transfer from bank two to bank one, then you are back in unlimited money territory.
This means there is no static limit to the amount of money that can be created. The limit is dynamic and depends on the interactions between banks. Specifically, it depends on the liquidity/solvency of a given bank. This means this limit is purely practical and more akin to friction, rather than a fundamental restriction in the math of banking/accounting. It's like how computers aren't turing machines because they have finite amounts of memory. There is no limit to how much memory a computer can have as long as you can manage to build a computer with that much memory.