Escape episode content when returning episode context as string #660
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Outdated suggestions cannot be applied.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.
Purpose of the change
Appears to help the LLM when there are newlines in the episode context.
Description
Escape episode content in DeclarativeMemory.string_from_episode_context.
Increases LongMemEval score by >1% in one run when using gpt-4.1-mini.
Use json.dumps() because it is a simple solution that always uses double-quotes. repr() may be more semantically natural but quotes inconsistently.
Implement similar changes in EpisodicMemory.
Type of change
How Has This Been Tested?
Manually tested with LongMemEval dataset. Tested once for LoCoMo regression. Does not appear to harm LoCoMo scores appreciably.
Checklist
Maintainer Checklist