An architect is designing the Messages API integration for a streaming chatbot. The frontend displays tokens as they are generated. After receiving a message_start event, the client receives repeated content_block_delta events, then unexpectedly receives an error event mid-stream. What is the correct handling strategy?

When an SSE stream is interrupted by an error event, the correct UX and architectural response is: close the connection cleanly, preserve and display the partial content already received (it was valid output), mark it as incomplete with a visual indicator, and present a retry option to the user. Option A (auto-retry without user awareness) degrades UX and wastes compute for long generations. Option B is incorrect — the Anthropic API does not provide a partial-retry offset; you must restart the full request from the beginning. Option C (buffer everything, display only on message_stop) defeats the purpose of streaming and creates bad UX; errors should surface immediately so the user isn't left waiting on a failed connection. Option D correctly prioritizes user transparency and graceful degradation.