fix: openai repsonses api error handling

[Unshure]

Description

Fix failing openai responses api integ test:

FAILED tests_integ/models/test_model_openai.py::test_context_window_overflow_integration[OpenAIResponsesModel-gpt-4o-mini-2024-07-18] - Failed: DID NOT RAISE <class 'strands.types.exceptions.ContextWindowOverflowException'>

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: Request Changes

The fix for stream() is correct and will resolve the failing integration test. However, the structured_output() method (line 366) has the same bug and wasn't fixed.

Review Details

• Critical: Apply the same fix to structured_output() at line 366 - it currently only catches BadRequestError, not APIError
• Testing: Consider adding a test for APIError in structured_output() to verify the fix

Once structured_output() is updated with the same error handling pattern, this will be good to merge.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!