fix child agent config override #1850
Open
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
Collaborator
|
Thank you! Could you add regression tests for the added logic? |
Verify that from_dict correctly propagates shared runtime parameters (model, logger, executor_kwargs) from parent to child agents while preserving child-specific configurations (authorized_imports, tools). This test ensures the fix for issue huggingface#1849 works correctly.
Author
|
Thanks for reviewing! This test verifies that the fix works correctly. It passes on my branch but fails on the main branch (as expected), confirming that the bug exists and the fix resolves it. Test behavior:
|
Author
|
Sorry, my code has some gaps and doesn't cover every scenario.😅 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Description
Fixes #1849
This PR implements a whitelist mechanism to prevent parent agent parameters from overriding child agent configurations during deserialization.
Changes
SHARED_PARAMSwhitelist containing only truly shared resources:model,verbosity_level,logger,executor_type,executor_kwargsMultiStepAgent.from_dict()to filter kwargs before passing to child agentsadditional_authorized_imports,max_steps, etc.) now stay independentTesting
Verified that child agents retain their custom
additional_authorized_importsafterfrom_dict().Related Issue
None