fix: forward structured output request params for OpenAI Chat Completions

[gautamsirdeshmukh]

Description

Equivalent to #2551 (fix for normal OpenAI provider)

#2551

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 new warnings.

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have reviewed and understand every line of code in this PR, including any generated by AI tools, and I can explain why it works
• My change is focused and reasonably small; I have split unrelated work into separate PRs
• 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.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[github-actions]

Assessment: Approve

Clean, focused bug fix that forwards configured request params (e.g. max_tokens, temperature) to the non-streaming parse() call in structured_output, while correctly dropping the streaming-only fields. The approach is consistent with the existing openai_responses.py sibling, and the new unit test asserts the full call shape in a single assert_called_once_with rather than per-field. Structured-output unit tests pass locally.

Review Categories

• Correctness: format_request produces stream/stream_options (since stream defaults to True), both of which are explicitly popped before parse(). The inline comment explaining why is helpful.
• Consistency: Mirrors the established pattern in openai_responses.py::structured_output, and is the Chat-Completions analogue of the already-merged fix(openai-responses): prevent tool list mutation across API calls #2551 fix.
• Testing: Good coverage of the param-forwarding behavior with a full-shape assertion. One minor note left inline re: the incidental tools=[] now being forwarded — worth a quick end-to-end confirmation against the live API if not already done.

Nicely scoped change with a clear, well-commented intent.