fix: chat agent integration, llama inference bug

backend/src/inference.py

@@ -71,7 +71,7 @@ def build_messages(system_prompt="", instruction=None, input=None, messages=None
             raise Exception("Unsupported message type: " + repr(type(message)))
 
     # shouldn't be necessary. maybe an assert instead?
-    messages = [normalize(msg) for msg in messages]
+    messages = [normalize(msg) for msg in messages or []]
     # default user message
     prompt = input
 
@@ -141,7 +141,7 @@ async def chat_completion(app,
 # llama.cpp
 async def local_chat_completion(app, messages, model, tools=[], opts={}, agent_run=None):
     if agent_run:
-        content_stream = agent_run.stream
+        content_stream = agent_run.get_output_stream()
     else:
         content_stream = Stream(app)