Because it's complex and I'm stuffing 30-50 PRs a day through it. 7 GHA workflows across four self-hosted runners.

I'm on my third iteration, after constantly log jamming previous versions. Most steps aren't "run pytest", they're gates that guard against an LLM's bias to continuously add more and more complexity to a system.

I'm aware of the irony of having a complex system to mitigate complexity, but the key difference is these rules bound complexity growth. If you're legitimately interested in the details, let me know. I'm too tired to write up much more but would be willing to drop in a LLM-authored summary of the details.