Feature request: include insertion point/caret in <CONTEXT_INFORMATION>

[cailmdaley]

Hello,

I'd like to thank the maintainers for your great work on this project! I'm not sure how feasible this is, but I think it would be very powerful if the insertion point or caret location could be denoted in the <CONTEXT_INFORMATION> that's passed to the AI enhancement. This would provide richer context about whether the user is continuing a sentence, and how the transcript relates to the rest of the information in the current window.

[Beingpax]

I didn't quite get what you're trying to say. Can you please expand this and provide the exact use case for how you're trying to use it?

[slumdev88]

@Beingpax simply speaking, they want to pass the contextual information of where they have their cursor in a text box (relative to the other information contained) so that the AI can determine if the first letter should be capitalised or not—and have the context of a continuing transcription.

For example, if I dictate a paragraph, I might go back to the middle of the paragraph (somewhere) and start dictating again, just to add on to a sentence. I want it to be formatted correctly and with the context of what it's following on from.

Mac OS Apps such as Wisprflow and Willow Voice are currently able to do this.

[cailmdaley]

thank you @slumdev88, that was exactly what I was trying to say.