fix: resolve string formatting error in MCP client error handling

[cagataycali]

Description

Fixes a TypeError: not all arguments converted during string formatting error that occurs when MCP error messages contain % characters (common in URL-encoded strings from MCP servers like Bedrock AgentCore).

Related Issues

Fixes #1244

Root Cause

In _handle_error_message(), the log call was:

self._log_debug_with_thread("ignoring non-fatal MCP session error", message)

The format string had no %s placeholder, but message was passed as an argument. When message contained % characters (e.g., unknown request id: abc%20123), Python's % formatting in _log_debug_with_thread would fail.

Solution

Add %s format specifier to the log message:

self._log_debug_with_thread("ignoring non-fatal MCP session error: %s", message)

Documentation PR

No documentation changes required.

Type of Change

• Bug fix (non-breaking change which fixes an issue)

Testing

• Added regression test test_handle_error_message_with_percent_in_message
• All 109 existing MCP tests pass
• hatch fmt --formatter ✅
• hatch fmt --linter ✅

Checklist

• I have read the CONTRIBUTING document
• I have added tests that prove my fix is effective
• My changes generate no new warnings

---

🦆

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!