feat: parallel tool calling for openai non streaming [LET-4593] (#5773)

* first hack

* clean up

* first implementation working

* revert package-lock

* remove openai test

* error throw

* typo

* Update integration_test_send_message_v2.py

* Update integration_test_send_message_v2.py

* refine test

* Only make changes for openai non streaming

* Add tests

---------

Co-authored-by: Ari Webb <ari@letta.com>
Co-authored-by: Matt Zhou <mattzh1314@gmail.com>

letta/adapters/simple_llm_stream_adapter.py

@@ -78,6 +78,13 @@ class SimpleLLMStreamAdapter(LettaLLMStreamAdapter):
             use_responses = "input" in request_data and "messages" not in request_data
             # No support for Responses API proxy
             is_proxy = self.llm_config.provider_name == "lmstudio_openai"
+            # Use parallel tool calling interface if enabled in config
+            use_parallel = self.llm_config.parallel_tool_calls and tools and not use_responses and not is_proxy
+
+            # TODO: Temp, remove
+            if use_parallel:
+                raise RuntimeError("Parallel tool calling not supported for OpenAI streaming")
+
             if use_responses and not is_proxy:
                 self.interface = SimpleOpenAIResponsesStreamingInterface(
                     is_openai_proxy=False,