I'd really like to get back to an autocomplete flow, ideally with some shared and optimized context with the relationship with my larger agent models.

But it seems like, by and large, even the faster models are now aimed at longer-running agentic flows and not sub-1s autocomplete. Or am I wrong about that?

You aren't wrong, the field is moving to a world where we do less in the code editor, so autocomplete is not needed any more. I've only manually edited code a few times in the last month. Haven't used autocomplete in 6+ months since I left Copilot to build my own agent harness (I'm now mainly using OpenCode)