3 Commits

Author	SHA1	Message	Date
Daniel Nakov	4261973467	bug: non-openai mode - don't default temp and top_p (#572) ... I haven't seen any actual errors due to this, but it's been bothering me that I had it defaulted to 1. I think best to leave it undefined and have each provider do their thing	2025-04-23 01:07:40 -04:00
Daniel Nakov	23f0887df3	bug: non-openai mode - fix for gemini content: null, fix 429 to throw before stream (#563) ... Gemini's API is finicky, it 400's without an error when you pass content: null Also fixed the rate limiting issues by throwing outside of the iterator. I think there's a separate issue with the second isRateLimit check in agent-loop - turnInput is cleared by that time, so it retries without the last message.	2025-04-22 20:37:48 -04:00
Daniel Nakov	eafbc75612	feat: support multiple providers via Responses-Completion transformation (#247) ... https://github.com/user-attachments/assets/9ecb51be-fa65-4e99-8512-abb898dda569 Implemented it as a transformation between Responses API and Completion API so that it supports existing providers that implement the Completion API and minimizes the changes needed to the codex repo. --------- Co-authored-by: Thibault Sottiaux <tibo@openai.com> Co-authored-by: Fouad Matin <169186268+fouad-openai@users.noreply.github.com> Co-authored-by: Fouad Matin <fouad@openai.com>	2025-04-20 20:59:34 -07:00