BestSoFarMinimiser behavior

Not sure if this is a bug or not, but `BestSoFarMinimiser` appears to not check the last step of the wrapped solver: 

```
solver = optimistix.BestSoFarMinimiser(optimistix.BFGS(rtol=1e-5, atol=1e-5))
ret = optimistix.minimise(lambda x, _: (x - 3.)**2, solver, 0.)
print(ret.value, ret.state.state.y_eval)

0.0 3.0
```