For high-throughput in-person ID Verifier flows, is it recommended to call MobileDocumentReader.prepare() before the operator starts a check and cache the prepared MobileDocumentReaderSession for one later requestDocument call? Or should apps only call prepare() after explicit user intent? If prewarming is supported what should invalidate a prepared session?

I’m building an in-person ProximityReader ID Verifier Display Only flow for venue age checks. Right now on iOS 26, we use a single MobileDocumentDisplayRequest with allowedDocumentTypes: [.photoID, .driversLicense] and only request ageAtLeast(21). For reliability and broad credential support, is that the recommended request shape for both Passport-derived Photo ID and mobile driver’s license / State ID? Or should apps implement separate request paths when they want to support both document families? Trying to optimize for the most predictable Wallet behavior. Thank you!

Trying to use the new built-in coding agents in Xcode (Claude / Codex), but running into a limitation with enterprise model setups. Our org accesses models through Microsoft Foundry (Azure-hosted endpoints), and we can connect to those models in Xcode using a custom endpoint / URL. That part works. However, that setup doesn’t seem to work with the built-in coding agents themselves. Those still appear to require direct account login or native API keys, with no way (that I can find) to point them at a custom endpoint or provider-backed deployment. Anyone figured out a way to get the agent experience working with enterprise setups like Foundry (or proxy layers)? Or is that not supported yet?