Streaming mode truncates response in main chat window due to missing delimiter after sources

When streaming mode is enabled, the chat widget drops a portion of the assistant's response. In non-streaming mode, full responses are returned correctly.

Root cause:

RAGChatRequestFilter.processStreaming() builds the sources ChatMessage without appending a trailing \n\n:

  // Streaming path — missing delimiter
  new ChatMessage("assistant", SOURCES_STRING2 + sources, searchResults);

  // Non-streaming path — delimiter present
  message.setContent(SOURCES_STRING2 + extractURLsAndformat(searchResults) + NL2 + message.getContent());
  

The chat application's non-streaming parser uses the regex

/Sources:([\s\S]*?)(?=\n\n|$)/

 to extract the sources block. Without the \n\n boundary, the regex consumes into the main content and the
remainder is dropped.

Steps to Reproduce

1. Enable streaming mode in the AI-LLM main chat application window
2. Ask a question that triggers RAG (collection search)
3. Observe that the response content is truncated or empty

Expected Behavior

Full response is rendered, identical to non-streaming mode.

Actual Behavior

Response content is partially or fully missing when sources are returned.