Python: Send empty text for GitHubCopilotAgent tool results without text - #10272

Motivation & Context

When a function tool given to GitHubCopilotAgent produces no text, the model receives the repr of a Python list as the tool result, for example [<agent_framework._types.Content object at 0x77287488b230>]. This happens when the tool returns None, an empty string, or only rich content such as an image.

The tool adapter falls back to str(result) when there is no text. That was correct while FunctionTool.invoke returned a string, but since #4331 it returns a list of Content items, so the fallback now produces the list repr.

Description & Review Guide

• What are the major changes?

  The adapter in _tool_to_copilot_tool now sends the joined text as is:

                   text = "\n".join(c.text for c in result if c.type == "text" and c.text)
                   return ToolResult(
  -                    text_result_for_llm=text or str(result),
  +                    text_result_for_llm=text,
                       result_type="success",
                   )

  A new parametrized test, test_tool_handler_returns_empty_text_when_tool_returns_no_text, covers a tool that returns None, "" and only an image. Without the fix all three cases fail, because text_result_for_llm is the Content list repr.

• What is the impact of these changes?

  Tools without a text result now report an empty string to the model instead of a repr with a memory address. Tools that return text are unchanged. For a tool that returns only rich content, the existing "does not support rich tool content" warning is still logged and the result text is empty.

• What do you want reviewers to focus on?

  An empty string is what the Copilot SDK sends for a handler that returns None (copilot.tools._normalize_result), and what ClaudeAgent sends in the same case, so I used the same value here.

Related Issue

Fixes #10271

This is a one-line correction of a leftover str(result) fallback from #4331, so I opened it together with the issue.

AI Assistance

• No material AI assistance was used.
• This is an AI-assisted contribution. I reviewed, understood, and verified all submitted content and accept responsibility for it.

AI assistance details: I used Claude Code as an assistant to help find the bug and to draft the fix, the test, the linked issue and this description. I did the final review myself: I read and understood every change, checked the repro and test results, and made the final decisions on what to submit.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR links to an agreed issue with no competing open PR, or the Related Issue section documents a trivial-change or repository-automation exception.
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.