Remove Codex named args limitation warnings from docs and cli #696
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
Contributor
|
Let's get this merged when this is in the GA version of Codex. |
localden
added
documentation
Contributor
Author
Of course. I also noticed there are other parts of the CLI that warns when picking Codex. I can take a look at that as well in the meantime. |
emanuelturis
changed the title
emanuelturis
changed the title
|
Hey guys codex has pushed a new version that allows for custom commands |
Contributor
Author
I'm waiting on the review, but you can already use it with Codex. The changes are purely informational as to the limitations. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
openai/codex@3592ecb adds named args to prompt, as well as numeric (positional) args.
It's currently only available in the alpha versions, but will probably be released soon assuming they keep the same pace.
I'm not sure if anything else besides the docs needs to be updated, but I believe it's compatible with the way Claude Code does things for example, as per this comment: // Support $1..$9 and $ARGUMENTS in prompt content.