[BWStearns]

> when to know it’s time to replace my synchronous inter service http requests with a queue

I've found that once it's inconveniently long for a synchronous client side request, it's less about the performance or metrics and more about reasoning. Some things are queue shaped, or async job shaped. The worker -> main app communication pattern can even remain sync http calls or not (like callback based or something), but if you have something that has high variance in timing or is a background thing then just kick it off to workers.

I'd also say start simple and only go to Kafka or some other high dev-time overhead solution when you start seeing Redis/Rabbit stop being sufficient. Odds are you can make the simple solution work.