Feature: Allow for templating of nested objects in instructions#574
Feature: Allow for templating of nested objects in instructions#574whoisarpit wants to merge 1 commit intogoogle:mainfrom
Conversation
eb3b49c to
012ef17
Compare
012ef17 to
cd10aa0
Compare
|
@Jacksunwei PTAL. |
|
Hi @whoisarpit and thanks to everyone who participated in this thread. We're currently doing some housekeeping on our pull request queue. Given the rapid pace of development and the number of updates since this was last active, there's a good chance this pull request needs to be caught up to the latest version. To help us keep our backlog focused on current pull requests, we are closing this as stale. If you're still interested in contributing to this change, could you please update to the very latest version of the library and create a new pull request? Our team will be glad to help with the refreshed PRs and answer any questions! Thanks for your contribution and understanding!” |
|
This is a good feature to have. @ryanaiagent could you help to review? |
|
Response from ADK Triaging Agent Hello @whoisarpit, thank you for your contribution! This is a great feature. For future PRs, please remember to include a Thanks again! |
|
Hi @whoisarpit, This PR has merge conflicts that require changes from your end. Could you please rebase your branch with the latest main branch to address these? Once this is complete, please let us know so we can proceed with the review. |
|
Closing due to inactivity. Please raise a new PR after you fix the conflicts. |
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_valuesfunction 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.