refactor: invert tau_agent/tau_ai dependency to break import cycle#332
Open
Shravanth007 wants to merge 1 commit into
Open
refactor: invert tau_agent/tau_ai dependency to break import cycle#332Shravanth007 wants to merge 1 commit into
Shravanth007 wants to merge 1 commit into
Conversation
tau_agent.loop and tau_agent.harness imported ModelProvider, CancellationToken, and the Provider*Event types from tau_ai, while every tau_ai adapter imports message/tool types from tau_agent — a two-way package cycle contradicting the documented one-way layering. Apply dependency inversion: the portable core now defines the provider contract (tau_agent/provider.py, tau_agent/provider_events.py) and tau_ai implements it. tau_ai.provider and tau_ai.events become pure re-export shims so all existing call sites keep working, and the classes remain the same objects so isinstance dispatch in the loop is unaffected. Add tests/test_layering.py guarding the boundary and class identity, and update the README/architecture docs to describe the inward-pointing dependency direction. Refs huggingface#317
Author
|
@alejandro-ao do check this PR! .Thanks , and let me know if there is anything else need to be done here |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
tau_agent.loop and tau_agent.harness imported ModelProvider, CancellationToken, and the Provider*Event types from tau_ai, while every tau_ai adapter imports message/tool types from tau_agent — a two-way package cycle contradicting the documented one-way layering.
Apply dependency inversion: the portable core now defines the provider contract (tau_agent/provider.py, tau_agent/provider_events.py) and tau_ai implements it. tau_ai.provider and tau_ai.events become pure re-export shims so all existing call sites keep working, and the classes remain the same objects so isinstance dispatch in the loop is unaffected.
Add tests/test_layering.py guarding the boundary and class identity, and update the README/architecture docs to describe the inward-pointing dependency direction.
Refs #317