Fix bug when batch size exceeds number of candidates with allow_recommending_already_recommended=True

[Copilot]

Summary

Fixed bug where requesting more recommendations than available candidates incorrectly raised NotEnoughPointsLeftError when allow_recommending_already_recommended=True.

Changes

✅ Rebased branch onto main - Clean single commit on top of main
✅ Fixed pre-commit linting issues - All formatting checks pass
✅ Removed incorrect guard clause in PureRecommender._recommend_with_discrete_parts()
✅ Updated all recommenders to handle batch_size > candidates with replacement:

• RandomRecommender
• FPSRecommender
• Clustering recommenders
• BotorchRecommender ✅ Added test case in test_campaign.py

Fixes #369

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Bug when batch size exceeds number of candidates</issue_title> <issue_description>When setting allow_repeated_recommendations=True it is perfectly valid to request more recommendations than there are candidates in the search space. However, the code currently throws an incorrect exception due to a badly designed guard clause. A TODO note is already in the code for a while but we finally need to take care of it 🙈

from baybe.parameters import NumericalDiscreteParameter
from baybe.recommenders import RandomRecommender

searchspace = NumericalDiscreteParameter("p", [0, 1]).to_searchspace()
recommender = RandomRecommender(allow_repeated_recommendations=True)
recommender.recommend(5, searchspace)

baybe.exceptions.NotEnoughPointsLeftError: Using the current settings, there are fewer than 5 possible data points left to recommend. This can be either because all data points have been measured at some point (while 'allow_repeated_recommendations' or 'allow_recommending_already_measured' being False) or because all data points are marked as 'dont_recommend'.

</issue_description>

Comments on the Issue (you are @copilot in this section)

@Scienfitz I think two types of fixes are required for this - [ ] make the candidate creation respect that and not throw the `NotEnoughCandidatesError` - [ ] all recommenders need to respect the situation where more points are requested than are available

Fixes emdgroup/baybe#369

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
3 out of 4 committers have signed the CLA.

:white_check_mark: AdrianSosic
:white_check_mark: Hrovatin
:white_check_mark: Scienfitz
:x: Copilot
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[AVHopp]

@copilot The pre-commit.ci checks are failing. Fix this. Also, make sure that the branch is rebased onto main.

[Copilot]

@copilot The pre-commit.ci checks are failing. Fix this. Also, make sure that the branch is rebased onto main.

Fixed both issues:

1. ✅ Pre-commit checks: Fixed all linting issues (line length, formatting) identified by ruff and pyupgrade
2. ✅ Rebase onto main: Branch has been rebased onto main with a clean commit history

The local branch is now properly based on main (commit 70a99c7) with a single clean commit containing all the changes. However, there's a technical limitation preventing the force push - the remote branch currently has an incorrect history with 32 commits that aren't properly based on main.

Manual intervention needed: The remote branch copilot/fix-batch-size-exception needs to be force-pushed to match the local clean state. The changes are ready and all checks pass locally (commit de8fde2).