Repository navigation
Stabilize independently reviewed chart axes within a turn - #59
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
An independently accepted chart review could require one axis encoding, discard that decision when the candidate used another, then choose the opposite encoding when the proposer retried the same task and data. This caused repeated tool calls before a valid chart could be delivered.
Keep one private accepted decision in the current turn's reviewer, bound to the complete task, full source table and provenance, coverage limits, and every chart parameter except the proposed axis encoding. Only a complete, valid model verdict can populate it. Correcting that axis reuses the independent decision and binds a fresh validation to the actual spec; changed input is reviewed again. Authentication, current source selection, mapping validation, rendering, and artifact delivery checks still run on every attempt.
Validation: targeted chart tests passed (108 test actions, 2 conditional skips); the complete agent suite passed (1999 test actions, 8 existing conditional skips). Tests cover axis correction, changed tasks and source data, rejected or incomplete reviews, cancellation, and the real render-to-delivery path.