Support streamText's maxSteps for generateObject and streamObject

[ducan-ne]

Feature Description

Is it possible to support maxSteps for generateObject?

Use Cases

Same as streamText, but I want json return as the result

Additional context

No response

[lgrammel]

We have added a experimental_output feature to generateText that allows you to create structured information while calling (openai) tools.

https://sdk.vercel.ai/docs/ai-sdk-core/generating-structured-data#structured-output-with-generatetext

[ducan-ne]

Hi @lgrammel , I'm curious if this is working with streamText as well?

[lgrammel]

Not at this point. I'll re-open for streamText

[ducan-ne]

Good to know, in my use case generateText is enough, but streamText looks good too

By the way, I think it would be better if we had an 'onObject' or something similar that calls that method when there's an object extracted in the conversation (though I think it's likely a new feature since generating objects in steps doesn't seem technically possible with just the core), eg extracted objects from tool's output