Skip passing thoughts to OpenAI compatible APIs because they don't support marking them as such #154
+22 −0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
…pport marking them as such.
felixarntz added the [Type] Bug 
| The following accounts have interacted with this PR and/or linked issues. I will continue to update these lists as activity occurs. You can also manually ask me to refresh this list by adding the If you're merging code through a pull request on GitHub, copy and paste the following into the bottom of the merge commit message. To understand the WordPress project's expectations around crediting contributors, please review the Contributor Attribution page in the Core Handbook. |
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
There is no way in the OpenAI
chat/completionsspecification to mark input message content as thoughts/reasoning. So far we're just passing all text through as regular content, which can lead to model confusion because it can't differentiate between actual model responses and thoughts from previous turns.Therefore, it's safer to skip them entirely. Thoughts should not matter too much for subsequent turns. Ideally this would be supported by the API, but the tradeoff of skipping is safer.