fix: Raise StreamableHTTPError on reconnection failure

[wukath]

Motivation and Context

Raise StreamableHTTPError on reconnection failure when the GET stream connection fails and exceeds MAX_RECONNECTION_ATTEMPTS instead of returning silently.

Currently, when the GET stream connection fails and exceeds MAX_RECONNECTION_ATTEMPTS, the transport receive loop returns silently. This prevents the failure from propagating out of the transport receive loop, causing downstream agents/sessions to hang rather than cleanly identifying the disconnection and reporting the failure.

Fixes google/adk-python#2615.

How Has This Been Tested?

• Added test_reconnect_failure_propagates_error to tests/shared/test_streamable_http.py to assert that complete reconnection failure propagates the StreamableHTTPError.
• Executed pytest locally to verify all transport tests pass.

Breaking Changes

No breaking changes. This corrects silent failures and hangs into expected transport exception propagation.

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

Additional context

[cubic-dev-ai]

All reported issues were addressed

<sub>Reply with feedback, questions, or to request a fix.

Re-trigger cubic</sub>