fix: harden rag streaming and queue status reporting

fastapi_modules/fastapi_leaudit/rag_engine/generator.py

@@ -77,7 +77,9 @@ async def generate_stream(
                     if payload == "[DONE]":
                         break
                     chunk = json.loads(payload)
-                    delta = chunk.get("choices", [{}])[0].get("delta", {})
+                    choices = chunk.get("choices") or []
+                    first_choice = choices[0] if choices and isinstance(choices[0], dict) else {}
+                    delta = first_choice.get("delta", {})
                     text = delta.get("content", "")
                     if text:
                         yield _sse_line(
@@ -141,4 +143,4 @@ async def generate_stream(
 
 
 def _sse_line(data: dict) -> str:
-    return f"data: {json.dumps(data, ensure_ascii=False)}\\n\\n"
+    return f"data: {json.dumps(data, ensure_ascii=False)}\n\n"