Skip to content

Conversation

@kujtimiihoxha
Copy link
Member

@kujtimiihoxha kujtimiihoxha commented Sep 30, 2025

This is a refactor for provider-model durability and a general boost in LLM performance increase across the board.

Some breaking changes:

  • If you have setup an openai compatible custom provider you need to change the type to openai-compat from openai
  • The old gemini type is now google

@meowgorithm meowgorithm changed the title wip Fantasy Integration Oct 1, 2025
@meowgorithm meowgorithm changed the title Fantasy Integration chore: fantasy integration Oct 1, 2025
@andreynering andreynering self-requested a review October 1, 2025 20:53
Copy link
Member

@andreynering andreynering left a 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.

  1. The machine stops after every tool call, and I have to keep typing continue. Despite of this, after every continue it's able to proceed.
Screenshot

Image

  1. Frequent errors on View and Edit tools. old_string not found in file and Invalid view parameters keeps happening even after many attempts.
Screenshot

Image

@kujtimiihoxha kujtimiihoxha mentioned this pull request Oct 27, 2025
13 tasks
@andreynering andreynering merged commit bc3858f into main Oct 27, 2025
17 checks passed
@andreynering andreynering deleted the crush-fantasy branch October 27, 2025 14:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants