ValueError: Found AIMessages with tool_calls that do not have a corresponding ToolMessage

[hyb91]

Through Langchain official case, case address: https://langchain-ai.github.io/langgraph/agents/multi-agent/#swarm

The error report is as follows:
Traceback (most recent call last):
File "D:\Langchain.venv\test\graph28.py", line 52, in
for chunk in swarm.stream(
~~~~~~~~~~~~^
{
^
...<6 lines>...
},config
^^^^^^^^
):
^
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel\main.py", line 2642, in stream
for _ in runner.tick(
~~~~~~~~~~~^
[t for t in loop.tasks.values() if not t.writes],
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...<2 lines>...
schedule_task=loop.accept_push,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel_runner.py", line 162, in tick
run_with_retry(
~~~~~~~~~~~~~~^
t,
^^
...<10 lines>...
},
^^
)
^
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel_retry.py", line 42, in run_with_retry
return task.proc.invoke(task.input, config)
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^
File "D:\Langchain.venvLib\site-packages\langgraph_internal_runnable.py", line 657, in invoke
input = context.run(step.invoke, input, config, **kwargs)
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel\main.py", line 3015, in invoke
for chunk in self.stream(
~~~~~~~~~~~^
input,
^^^^^^
...<10 lines>...
**kwargs,
^^^^^^^^^
):
^
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel\main.py", line 2642, in stream
for _ in runner.tick(
~~~~~~~~~~~^
[t for t in loop.tasks.values() if not t.writes],
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...<2 lines>...
schedule_task=loop.accept_push,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel_runner.py", line 162, in tick
run_with_retry(
~~~~~~~~~~~~~~^
t,
^^
...<10 lines>...
},
^^
)
^
File "D:\Langchain.venv\Lib\site-packages\langgraph\pregel_retry.py", line 42, in run_with_retry
return task.proc.invoke(task.input, config)
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^
File "D:\Langchain.venv\Lib\site-packages\langgraph_internal_runnable.py", line 657, in invoke
input = context.run(step.invoke, input, config, **kwargs)
File "D:\Langchain.venv\Lib\site-packages\langgraph_internal_runnable.py", line 394, in invoke
ret = context.run(self.func, *args, **kwargs)
File "D:\Langchain.venv\Lib\site-packages\langgraph\prebuilt\chat_agent_executor.py", line 616, in call_model
model_input = _get_model_input_state(state)
File "D:\Langchain.venv\Lib\site-packages\langgraph\prebuilt\chat_agent_executor.py", line 595, in _get_model_input_state
_validate_chat_history(messages)
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^
File "D:\Langchain.venv\Lib\site-packages\langgraph\prebuilt\chat_agent_executor.py", line 246, in _validate_chat_history
raise ValueError(error_message)
ValueError: Found AIMessages with tool_calls that do not have a corresponding ToolMessage. Here are the first few of those tool calls: [{'name': 'book_flight', 'args': {'from_airport': 'BOS', 'to_airport': 'JFK'}, 'id': 'call_KUbGSv8HoAu5XIvfHWo7yjhM', 'type': 'tool_call'}].

Every tool call (LLM requesting to call a tool) in the message history MUST have a corresponding ToolMessage (result of a tool invocation to return to the LLM) - this is required by most LLM providers.
For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/INVALID_CHAT_HISTORY
During task with name 'agent' and id 'a0da7fde-e414-8f88-4962-70c5740dad23'
During task with name 'hotel_assistant' and id '2a301e57-a7c6-36a5-de74-bbf23c1b743e'