9390fba768
Reduce maximum replies to 2500 tokens and make them even for both GPT-3.5 and 4 Account for 400+ tokens in function definitions (this was unaccounted for) |
||
---|---|---|
.. | ||
lib/modules | ||
models | ||
requests | ||
serializers | ||
shared | ||
support | ||
system | ||
plugin_spec.rb |