Handle OpenAI refusals and missing message content

[malai001]

Description

Fixes #491.

The realtime OpenAI provider previously returned
ScoredOutput(score=1.0, output=None) when message.content was
missing, causing refusal or content-filtered responses to be reported
as successful extractions.

This change aligns the realtime provider with the batch provider by:

• Raising InferenceRuntimeError when message.content is None.
• Surfacing the refusal reason when message.refusal is present.
• Raising a descriptive error when neither content nor refusal is available.
• Adding regression tests for successful responses, refusals, and missing-content responses.

How Has This Been Tested?

• Added regression tests covering:
  • Successful completion
  • Refusal response (message.refusal)
  • Missing message.content
• Ran:

python -m pytest tests/provider_schema_test.py

Result:

31 passed, 10 warnings

Checklist

• I have read the contribution guidelines.
• I have added or updated tests where appropriate.
• I have verified that all tests pass locally.
• My changes are limited to the scope of this fix.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[github-actions]

⚠️ Branch Update Required

Your branch is 1 commits behind main. Please update your branch to ensure CI checks run with the latest code:

git fetch origin main
git merge origin/main
git push

Note: Enable "Allow edits by maintainers" to allow automatic updates.