fix(web): avoid eval history crash when toolUses is null

[pandego]

Please ensure you have read the contribution guide before creating a pull request.

Link to Issue or Description of Change

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

• Closes: Playground eval history: clicking failed eval result crashes with 'e is not iterable' in formatToolUses #4657
• Related: Playground eval history: clicking failed eval result crashes with 'e is not iterable' in formatToolUses #4657

2. Or, if no issue exists, describe the change:

Problem:
Failed eval history entries can crash the web UI when intermediateData.toolUses is missing/null. formatToolUses currently iterates directly over that value and throws TypeError: e is not iterable.

Solution:
Add a null guard in formatToolUses so missing toolUses is treated as an empty list.

Testing Plan

Unit Tests:

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

Passed locally:

• .venv/bin/pytest tests/unittests/evaluation/test_eval_config.py
• Result: 7 passed

Manual End-to-End (E2E) Tests:

Not run in this environment. This patch is a minimal defensive guard on the affected formatter path.

Checklist

• I have read the CONTRIBUTING.md document.
• 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.

Additional context

This is intentionally minimal (1-line behavior change) to reduce risk and keep review focused.

[gemini-code-assist]

Note

Gemini is unable to generate a summary for this pull request due to the file types involved not being currently supported.

[rohityan]

Hi @pandego ,Thank you for your contribution! We appreciate you taking the time to submit this pull request. Your PR has been received by the team and is currently under review. We will provide feedback as soon as we have an update to share.

[rohityan]

Hi @wyf7107 , can you please review this.

[pandego]

Refreshed this branch onto current main and force-pushed.

The original change was targeting an older generated browser bundle file. I ported the null guard to the active bundle referenced by src/google/adk/cli/browser/index.html so the eval history path no longer crashes when toolUses is missing.

Validation run:

• uv run pytest tests/unittests/cli/utils/test_cli_eval.py tests/unittests/cli/utils/test_evals.py -q