[CB] fix scheduler constraint max tokens

[sducouedic]

The continuous batching scheduler checks that the request (ie. prompt + requested tokens) would fit the max_context_len, but didn't account for the fact that the last generated token is a "free" one that doesn't need to be stored in a block

[github-actions]

👋 Hi! Thank you for contributing to vLLM support on Spyre.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, first install the linting requirements, then run format.sh and commit the changes. This can be done with uv directly:

uv sync --frozen --group lint --active --inexact

Or this can be done with pip:

uv pip compile --group lint > requirements-lint.txt
pip install -r requirements-lint.txt
bash format.sh

Now you are good to go 🚀

[yannicks1]

related to #320