-
Notifications
You must be signed in to change notification settings - Fork 822
feat: refactor providers and improve system prompt #1171
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
4a557db to
d786161
Compare
d9d9fd5 to
c58a4d4
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I gave this some testing, and it is pretty good overall!
I didn't review all the code because it's a lot, but looks much cleaner and more organized than before.
Below I added a couple of bugs I found when using the OpenAI compatible providers (OpenRouter and Hyper) specifically. Those bugs are not present for OpenAI or Anthropic.
- The machine stops after every tool call, and I have to keep typing
continue. Despite of this, after everycontinueit's able to proceed.
- Frequent errors on
ViewandEdittools.old_string not found in fileandInvalid view parameterskeeps happening even after many attempts.
a604c3c to
ad881b2
Compare
ad881b2 to
b45dcfe
Compare
835fbc1 to
5d42049
Compare
Signed-off-by: Carlos Alexandro Becker <[email protected]>


This is a refactor for provider-model durability and a general boost in LLM performance increase across the board.
Some breaking changes:
typetoopenai-compatfromopenaigeminitype is nowgoogle