This moves all the env var reading into one central module
and logs the loaded config once at startup which should
help in troubleshooting user server logs
* app: restart server on failure
* fix linter
* address comments
* refactor log directory creation to be where logs are written
* check all log dir creation errors
This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems. This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.
