Gregor Martynus
Gregor Martynus
Thank you James & Matt for sharing your use cases. I'm not sure what the implications would be in terms of added code complexity. If you consider to implement it...
Pull requests welcome :) Thanks for your help!
yes, I think that should be > Default: `false` if running in a CI environment, `true` otherwise But maybe double check the code to make sure :)
very sorry for all the trouble! I'll be looking at this today 🙇🏼
I also cannot reproduce the problem when testing it end-to-end. The original code from @abhi-slash-git is incorrect, the order of the content items in the assistant message is wrong, it's...
I have no objections to support comments in `.releaserc.json`, I'm not sure if anyone else sees problems with that? Let's leave the issue open for a while to see what...
@nspady not sure how the change of Anthropic's model naming convention relates to this isssue?
Ah the example code shared by @rbitar [above](https://github.com/vercel/ai/issues/7729#issuecomment-3156256996) uses the wrong model identifier.
> ```ts > prepareStep: async ({ stepNumber, steps, messages }) => { > // Compress conversation history for longer loops > if (messages.length > 20) { > return { >...
I could imagine to have semantic-release as-is, but offer a `@semantic-release/core` package without any plugins loaded for more advanced users.