PatchToolCallsMiddleware.before_agent

[khteh]

What does this do? It seems to be a no-op and just passes the input as the output?

This creates a duplicate console output as well which is confusing:

================================ Human Message =================================

<snip>    

================================ Human Message =================================

<snip>    

================================== Ai Message ==================================

<snip>

[hwchase17]

if there are tool calls without a tool call response, this fixes that (otherwise some model providers will errror)

[khteh]

Did you refer to this one https://docs.langchain.com/oss/python/langgraph/errors/INVALID_CHAT_HISTORY and is it still valid? I have this retry logic which patches the missing tool call response. Happy to remove it if this is not needed anymore?

            except Exception as e:
                # https://langchain-ai.github.io/langgraph/troubleshooting/errors/INVALID_CHAT_HISTORY/
                logging.exception(f"ChatAgent exception! {str(e)}, repr: {repr(e)}")
                if attempt == 2:
                    return result
                if "Found AIMessages with tool_calls that do not have a corresponding ToolMessage" in str(e):
                    #state = await current_app.agent.with_config(config).aget_state() XXX: This doesn't work! Why!?!
                    state = await self._agent.aget_state({"configurable": {"thread_id": config.thread_id, "user_id": config.user_id}})
                    tool_messages = set()
                    outstanding_tool_call_ids = set()
                    # Assumption: state.messages is chronologically ordered
                    for message in reversed(state.values["messages"]):
                        msg = ChatMessage.from_langchain(message)
                        if msg.type == "tool":
                            tool_messages.add(msg.tool_call_id)
                        elif msg.type == "ai" and len(msg.tool_calls):
                            for tc in msg.tool_calls:
                                if tc["id"] not in tool_messages:
                                    outstanding_tool_call_ids.add(tc["id"])
                    for id in outstanding_tool_call_ids:
                        # provide ToolMessages that match existing tool calls and call graph.invoke({'messages': [ToolMessage(...)]}). 
                        # NOTE: this will append the messages to the history and run the graph from the START node.
                        await self._agent.with_config(config).ainvoke({'messages': [ToolMessage(content="I don't know!", tool_call_id=id)]})