Simple LLM-based triage of integration test failures

[twz123]

Description

Construct a prompt that includes excerpts from the integration test output and the k0s logs. Ask for classification and the reasoning behind it. Send it to gpt-4o.

This is just a simple model call, not anything remotely agentic, but this is what's doable with the plain GitHub token, without having to provision any other API keys, credit cards, or whatnot.

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update

How Has This Been Tested?

• Manual test
• Auto test added

Checklist

• My code follows the style guidelines of this project
• My commit messages are signed-off
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules
• I have checked my code and corrected any misspellings