Feature: Allow for templating of nested objects in instructions #574
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Outdated suggestions cannot be applied.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.
Fixes #575
Summary
Adds support for nested dot-separated references in instruction templates. Users can now access deeply nested values in the state object using a simple dot notation, with optional markers at any level of the path.
This is useful when templating structured data from a previous LlmAgent using output_schema.
Changes
_populate_values
function to handle nested dot-separated references?
suffix (e.g.,{user?.profile?.name?}
)Examples
Before:
After:
Use Cases
This feature enables more flexible template interpolation, allowing for cleaner, more organized state structures while maintaining backward compatibility with the existing flat state model.