FoundationModels Content Sanitizer Blocking Legitimate Text Processing

I'm developing a macOS application using the FoundationModels framework (LanguageModelSession) and encountering issues with the content sanitizer blocking legitimate text input.

** Issue Description:** The content sanitizer is flagging text strings that contain certain substrings, even when they represent legitimate technical content. For example:

• F_SEEL_SEX1S.wav (sE Electronics SEX1S microphone model)
• Technical product identifiers
• Serial numbers and version codes

** Broader Concern:** The content sanitizer appears to be applying restrictions that seem inappropriate for user-owned content. Even if a filename were something like "human sex.wav", users should have the right to process their own legitimate files on their own devices without content filtering interference.

** Error Messages:** SensitiveContentSettings: Sanitizer model found unsafe content in value FoundationModels.LanguageModelSession.GenerationError error 2

** Questions:**

1. Is there a way to disable content sanitization for processing

user-owned content? 2. What's the recommended approach for applications that need to handle arbitrary user text? 3. Are there APIs to process personal content without filtering restrictions?

** Environment:**

• macOS 26.0
• FoundationModels framework
• LanguageModelSession

Any guidance would be appreciated.