Fix #754: remove hard-coded 1:2 column limit in chat.R #767
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
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
hadley
reviewed
Oct 2, 2025
| tokens_acc[, 1] <- tokens_acc[, 1] + tokens_acc[, 3] | ||
| # Then drop cached tokens counts | ||
| tokens_acc <- tokens_acc[, 1:2] | ||
| tokens_acc <- tokens_acc[,, drop = FALSE] |
There was a problem hiding this comment.
It seems like your new code will not drop the cached tokens count which will mean that they get double counted?
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
|
Thanks for the reviewing, Hadley! Turns out the bug wasn't in get_tokens() at all so I've reverted that. The actual issue was in convert_from_type() in chat-structured.R: when processing arrays of nested objects, the function was passing data frames directly to list2DF(), which only extracted the first 2 rows. |
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Outdated suggestions cannot be applied.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.
Previously, the code
tokens_acc[, 1:2]truncated the output to only the first two columns, causing chat_structured_parallel() and convert_from_type() to return only two rows.The change removes this hard-coded limit, ensuring all columns are retained.
Notes on CI:
chat_structured_parallel()andconvert_from_type()passes all tests.