Why Postgres should be doing this?
Not every client creates a lot of connections and spinning up PgBouncer is easy.
On the other hand, debugging async multithreaded complex code is hard.
If you give your agent a `bash` or `python -c` tool, it starts a separate process that produces some output and then exits. After that, only the output and the exit code are available.
In contrast, `eval` runs the code in the same execution context as the agent loop. When `eval` finishes, that execution context still exists. For example, any functions defined during an `eval` call remain available for later use.
I remember a cool implementation detail about the earliest Knoppix version (don't remember which one) I had that was documented somewhere on that disc - when constructing a release filesystem image, the boot process was instrumented to get an ordered list of files being read. Then that list was fed into an image building program so when written to a CD, the files will be organized in an optimal order so a linear read with some readahead would get you a better boot time.