Fix restored answer formatting and constrain finalizer citations - #60
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Restored session messages exposed internal
[cite:evidence:...]markers because they bypassed the formatter used by live run responses. Restoration now uses the same numbered-reference projection, while canonical answers and user messages remain unchanged.Finalization accepted arbitrary strings as evidence IDs and could exhaust its repair attempt with invalid citations after successful frame analysis. After context gathering, its structured-output schema now limits answer and memory references to supplied excerpt IDs and aliases. Persisted-evidence validation remains authoritative. Citation failures additionally log whether evidence was missing or conflicting, without logging the identifier or answer.
Validation:
The reported run's logs confirm two normally completed model responses rejected at citation validation. They do not retain the rejected identifier, so this change does not claim to reconstruct the exact bad reference.