fix(anthropic): handle plain string in part_to_message_block

[AliMuhammadAslam]

Problem

part_to_message_block() in anthropic_llm.py iterates over response_data["content"] without checking whether the value is a list or a plain string. When a tool returns a response where content is a string, the loop yields one character per iteration, so the assembled result is individual characters joined by newlines instead of the full text.

LoadSkillResourceTool is a concrete example: it returns {"skill_name": ..., "file_path": ..., "content": "<file text>"} where content is a string, not a list.

Closes #5358

Fix

Added an isinstance(response_data["content"], str) check before the loop. When content is a string it is passed through directly. When it is a list, the existing item-by-item join logic runs as before.

Testing

Added test_part_to_message_block_with_string_content to tests/unittests/models/test_anthropic_llm.py. The test creates a function response matching the LoadSkillResourceTool shape and asserts the full string comes through unchanged.

All existing part_to_message_block tests continue to pass.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[adk-bot]

Response from ADK Triaging Agent

Hello @AliMuhammadAslam, thank you for your contribution!

Before we can merge this PR, you need to sign the Contributor License Agreement (CLA). It seems that the CLA check has failed.

For more details, please review our contribution guidelines.

Thank you!

[AliMuhammadAslam]

I have signed the CLA.