* Changes to lmstudio to fix JSON decode error
* black formatting
* properly handle context overflow error (propogate exception up the stack with recognizable error message) + add backwards compat option to use completions endpoint
* set max tokens to 8k, comment out the overflow policy (use memgpt's overflow policy)
* 8k not 3k
---------
Co-authored-by: Matt Poff <mattpoff@Matts-MacBook-Pro-2.local>
Co-authored-by: cpacker <packercharles@gmail.com>
12ca6e98af