refactor(clv): drop _prior suffix backwards-compat shim

[anevolbap]

Summary

Removes the _prior-suffix backwards-compat shim from CLVModel. This was added in #1498 as a v1.0 deprecation. #1516 is the CLV-deprecations umbrella; this PR covers the first item there and leaves the rest as follow-ups.

Three sites in pymc_marketing/clv/models/basic.py:

• The deprecated_keys rename loop in __init__.
• The _rename_posterior_variables call inside build_from_idata.
• The _rename_posterior_variables method itself.

Two deprecation tests in tests/clv/models/test_basic.py are dropped (test_backwards_compatibility_with_old_config, test_deprecation_warning_on_old_config).

Mechanical follow-up: covariate convergence tests in test_beta_geo.py and test_modified_beta_geo.py still passed _prior-suffixed keys (relying on the shim's silent rename). The same applied to docs/source/notebooks/clv/dev/bg_nbg_covariates_test_issues.ipynb. Renamed those keys to drop the suffix so they exercise the same priors directly.

Note on timing

This is a hard breaking change: users still passing _prior-suffixed keys will get a silent fallback to defaults, and saved netCDFs with _prior-suffixed posterior vars will not load cleanly. The original intent was a v1.0 cut. v1.0 (#2108) is still open. Can hold this PR until v1.0 is being cut, or merge now to start closing out the deprecations early. Preference?

Remaining CLV deprecations tracked in #1516 (clv.utils.clv_summary, ShiftedBetaGeoModelIndividual per #2157, unused distribution blocks per #2158, plotting parameter, fit(fit_method=...), CLVModel.build_with_data) are intentionally out of scope and would land as separate PRs.

Test plan

• pre-commit run on the touched files: pass
• pytest tests/clv/: 313 passed, 17 skipped
• Targeted convergence tests after the key rename: 4/4 pass

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 93.88%. Comparing base (1a3f0d0) to head (c5fc5b2).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2576      +/-   ##
==========================================
- Coverage   93.90%   93.88%   -0.02%     
==========================================
  Files          92       92              
  Lines       14089    14078      -11     
==========================================
- Hits        13230    13217      -13     
- Misses        859      861       +2     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB