Fix: Handle content moderation in responses.parse()

[veeceey]

Summary

Fixed responses.parse() to properly handle content moderation responses. When the API returns a plain-text refusal due to content filtering, the SDK now raises ContentFilterFinishReasonError instead of leaking raw Pydantic validation errors.

Problem

When using responses.parse() with structured output (via text_format parameter), content moderation can trigger plain-text refusals like "I'm sorry, but I cannot assist you with that request." These refusals are not valid JSON and cause pydantic_core.ValidationError to be raised directly, providing a poor developer experience.

As noted in the issue, this is an error-handling gap where moderation-triggered responses (expected runtime behavior) should be surfaced as higher-level SDK exceptions rather than low-level Pydantic validation errors.

Solution

Modified parse_text() to:

1. Wrap JSON parsing in a try-except block
2. Check for response.incomplete_details.reason == "content_filter" to detect moderation
3. Raise ContentFilterFinishReasonError for content filter cases
4. Raise APIResponseValidationError with helpful context for other parsing failures

Testing

Added comprehensive test cases:

• ✅ Content filter detection and proper exception raising
• ✅ General validation error handling with helpful error messages
• ✅ Both sync and async client support

Impact

• Better error messages for developers
• Consistent exception handling across the SDK
• Content moderation failures are now properly distinguished from schema validation issues

Fixes #2834

[veeceey]

Ready for review and merge. All tests passing.