fix: stop leaking Python tracebacks in streaming SSE error responses (#20850)

When a guardrail (e.g. Zscaler AI Guard) or other exception is raised
during streaming, the error handler in `async_data_generator` includes
the full Python traceback in the SSE response sent to clients:

    error_msg = f"{str(e)}\n\n{traceback.format_exc()}"

This leaks internal server details (file paths, line numbers, call
stacks) to end users. The traceback is already logged server-side via
`verbose_proxy_logger.exception()`, so including it in the client
response is unnecessary.

Change to only include the exception message (`str(e)`) in the SSE
error payload, consistent with how `StreamingCallbackError` is already
handled.

Fixes #20610

litellm/proxy/proxy_server.py

@@ -4705,8 +4705,10 @@ async def async_assistants_data_generator(
         if isinstance(e, HTTPException):
             raise e
         else:
-            error_traceback = traceback.format_exc()
-            error_msg = f"{str(e)}\n\n{error_traceback}"
+            # Only include the error message, not the traceback.
+            # The traceback is already logged above via verbose_proxy_logger.exception().
+            # Including it in the SSE response leaks internal details to clients.
+            error_msg = str(e)
 
         proxy_exception = ProxyException(
             message=getattr(e, "message", error_msg),
@@ -4856,8 +4858,10 @@ async def async_data_generator(
         elif isinstance(e, StreamingCallbackError):
             error_msg = str(e)
         else:
-            error_traceback = traceback.format_exc()
-            error_msg = f"{str(e)}\n\n{error_traceback}"
+            # Only include the error message, not the traceback.
+            # The traceback is already logged above via verbose_proxy_logger.exception().
+            # Including it in the SSE response leaks internal details to clients.
+            error_msg = str(e)
 
         proxy_exception = ProxyException(
             message=getattr(e, "message", error_msg),