Repository navigation
Conversation
History was text only, so a follow-up had to rediscover the dataset, places, and filters, and could not change a chart it had drawn. The browser now keeps each tool call's arguments and sends the ones that worked back with the history; the server replays them as tool calls with a placeholder result. Only the agent's own tool names are accepted, within a size bound, and rows are never kept.
duaneatat
marked this pull request as draft
November 12, 2026 22:39
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-ups had only the earlier answer's text, so the model rediscovered the dataset and places each time and couldn't change a chart it had drawn. The follow-up eval case was Haiku's weakest (82%).
get_timeseriesandrender_chartcalls