Both Astra and Sol 6.1 do it, and Sol is even worse as it leaks through everywhere. Whenever it issues a subagent prompt it's just a total vomit of tokens mixed up together.

No, newer models talk to themselves in this degenerated form of English all the time. It's a known problem that deep frying transformers with RL reduces CoT legibility, and the only known way around it is the Most Forbidden Technique - grading chains of thought.