New attempt

modules/llama_cpp_server.py

@@ -146,8 +146,9 @@ class LlamaServer:
             pprint.PrettyPrinter(indent=4, sort_dicts=False).pprint(printable_payload)
             print()
 
-        # Make a direct request with streaming enabled using a context manager
-        with self.session.post(url, json=payload, stream=True) as response:
+        # Make a request with streaming enabled
+        response = self.session.post(url, json=payload, stream=True)
+        try:
             response.raise_for_status()  # Raise an exception for HTTP errors
 
             full_text = ""
@@ -185,6 +186,9 @@ class LlamaServer:
                     print(f"Problematic line: {line}")
                     continue
 
+        finally:
+            response.close()
+
     def generate(self, prompt, state):
         output = ""
         for output in self.generate_with_streaming(prompt, state):