Add truncate argument to uniformity_test()

[florence-bockting]

Summary

Currently, uniformity_test() determines automatically whether the truncated Cauchy combination test (CCT) should be used or not. This decision is based on the test value (POT and PRIT -> truncated CCT; PIET -> untruncated CCT).
However, there are situations in which the user should be able to change this default behaviour by customising the truncation option.

This PR adds a truncate argument to uniformity_test() which is by default NULL in which case it mimics the original behaviour of automatic detection based on the test value.

Copyright and Licensing

By submitting this pull request, the copyright holder is agreeing to
license the submitted work under the following licenses:

• Code: BSD 3-clause (https://opensource.org/licenses/BSD-3-Clause)
• Documentation: CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/)

[github-actions]

This is how benchmark results would change (along with a 95% confidence interval in relative change) if d4f3408 is merged into master:

• ✔️as_draws_array: 138ms -> 138ms [-0.71%, +0.53%]
• ✔️as_draws_df: 35.2ms -> 35.7ms [-1.29%, +4.4%]
• ✔️as_draws_list: 161ms -> 162ms [-0.13%, +1.55%]
• ✔️as_draws_matrix: 29ms -> 28.9ms [-0.71%, +0.2%]
• ✔️as_draws_rvars: 120ms -> 120ms [-2.13%, +0.91%]
• ✔️summarise_draws_100_variables: 790ms -> 790ms [-0.25%, +0.18%]
• ✔️summarise_draws_10_variables: 84.4ms -> 84.4ms [-0.51%, +0.49%]
  Further explanation regarding interpretation and methodology can be found in the documentation.

[paul-buerkner]

Looks good. Thank you!