fix(tests): fix flaky tests to accept string or number

[lizradway]

Description

Fix flaky assertion in test_chat_completions_agent_invoke — the model sometimes responds with the word "four" instead of the digit "4" when asked "What is 2+2?". The assertion now accepts either form.

Related Issues

N/A

Documentation PR

N/A

Type of Change

Bug fix

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[github-actions]

Assessment: Comment

The fix is reasonable — LLMs are non-deterministic and can respond with either "4" or "four" to a math question. One missed instance of the same pattern exists in test_reasoning_content_multi_turn (line 72) that should also be updated for consistency.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[notowen333]

I wonder also if we should follow up a scan for similar assertions that should be widened