Eric Dubé

I updated the text command a while ago and it should be working, so I'm gonna try this out now.

I was able to find a big of explanation on this on [OpenAI forums](https://community.openai.com/t/why-was-max-tokens-changed-to-max-completion-tokens/938077/4). It seems to be the case that OpenAI broke backwards compatibility because some clients were using...

Note to future self: OpenAI docs refer to `max_output_tokens` instead of `max_completion_tokens`; it appears to be identical so that's likely what's preferred.

@AbhiSharmaNIT much appreciated! I've assigned you. Let me know if you need any direction. You'll find documentation for the ai module in the wiki

> Is there any updates now? So far we've added a config option to remove the requirement of a `api.` subdomain: ```json "experimental_no_subdomain": true, ```

This is no longer an issue: 3666b9f3a25127909940c988164ff61ec3c2ea99

> Is puter a real operating system ### Short Answer We call Puter a high-level distributed operating system because it sits on top of a traditional/regular/"device-bound" OS and offers to...

We've discussed this idea before actually. This will be a good intermediate feature before we implement some kind of instant messaging in Puter, or maybe something that could continue to...

[ai] I've updated the PR with several security and code quality improvements: 1. Added CSRF protection using state parameter for OAuth flows 2. Improved cookie security settings based on environment...

[ai] I've implemented a significant improvement to the OAuth functionality by creating a separate `oauth_providers` table. This change addresses the feedback about not modifying the user table directly and allows...