fix: Sampling for List columns with min_length > 32

[Copilot]

Fix List column sampling when min_length > 32

• Add test to reproduce the issue with min_length=33
• Fix the max calculation in List._sample_unchecked to handle min_length > 32
• Run tests to verify the fix
• Run code review
• Run security check
• Fix mypy errors in test_list.py

Summary

Fixed a bug where sampling would fail with ValueError: low >= high for List columns when min_length > 32 and max_length is not specified.

Changes made:

1. Modified dataframely/columns/list.py: Updated List._sample_unchecked method to calculate default_max = max(32, min_len) ensuring the max parameter is always greater than min when max_length is not specified
2. Added test in tests/column_types/test_list.py: Parametrized test covering min_length values of 0, 10, 33, and 100
3. Fixed mypy errors: Added cast import and used it to properly type the result of list.len().min()

Test results:

• All 23 list-specific tests pass
• All 609 column type tests pass
• All 311 sampling-related tests pass
• Pre-commit checks pass (including mypy)
• Code review: No issues found
• Security scan: No vulnerabilities found

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Sampling fails for List column with min_length>32</issue_title>
<issue_description>The following test fails with ValueError: low >= high.

import dataframely as dy
from dataframely.testing import create_schema

create_schema("test", {"a": dy.List(dy.Int64(), min_length=33)}).sample()

The problem is probably a wrong setting of the max argument in the following line:

dataframely/columns/list.py
</issue_description>

<agent_instructions>Make sure to first reproduce the issue with a failing test in the correct place in the codebase.</agent_instructions>

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

• Fixes Sampling fails for List column with min_length>32 #247

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 100.00%. Comparing base (b813ac9) to head (e1116b3).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff            @@
##              main      #248   +/-   ##
=========================================
  Coverage   100.00%   100.00%           
=========================================
  Files           53        53           
  Lines         3066      3068    +2     
=========================================
+ Hits          3066      3068    +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.

[jjurm]

@copilot Run pixi run pre-commit run and fix mypy errors

[Copilot]

@copilot Run pixi run pre-commit run and fix mypy errors

Fixed in e1116b3. Added cast import and used it to properly type the result of list.len().min() to resolve the mypy operator type errors.