fix: ignore usage-only responses (except for BIDI mode)

[r4inee]

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

• Closes: bug: Code execution flow emits contentless usage-only final event, preventing LLM loop from resuming #1245

Problem:
In ADK Java code execution flows, if the model response that contains executable code also has usageMetadata, ADK emits an extra contentless usage-only event after the codeExecutionResult event. That extra event is considered final=true, so BaseLlmFlow stops the loop and does not call the LLM again with the code execution result.

Solution:
Skipping metadata only events unless its in BIDI mode - aligns with adk-python behaviour.

Testing Plan

• Added unit test to ensure 2nd inference call
• Added unit to ensure it doesn't affect BIDI mode

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

Please include a summary of passed java test results.

Manual End-to-End (E2E) Tests:

Testing using example mentioned in #1245

Checklist

• I have read the CONTRIBUTING.md document.
• My pull request contains a single commit.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

[r4inee]

adk-python seems to fork the logic in LIVE/BIDI mode - mainly kept in consistent with the logic below for now to avoid a larger change.