ollama - 💡(How to fix) Fix LangChain: chatollama invocation fails when messages contain only SystemMessage/AIMessage without any HumanMessage [1 participants]

"""
Processes messages using LLM with tools when required.

Args:
    state: Current state containing messages and tool requirement
    
Returns:
    Dict containing updated messages
"""
info = runtime.execution_info
if info.node_attempt > 1:
    print("sleeping for 60 seconds before retrying.")
    await asyncio.sleep(60)     
# Create the prompt template with system prompt and messages
agent_description = AGENT_DESCRIPTION
prompt = PromptTemplate.from_template(agent_description)
system_message = [SystemMessage(content=prompt.format(current_date=state["current_date"], skills_description=state["skills_description"]))]

#add systemmessage to the beginning of the messages to be summarized so that it is included in the summary.
state["messages"] = system_message + state["messages"]

summarization_result = await asummarize_messages(
    state["messages"],
    running_summary=state.get("summary"),
    model=llm,
    max_tokens=10000,
    max_tokens_before_summary=5000,
    max_summary_tokens=1000,
    initial_summary_prompt=DEFAULT_INITIAL_SUMMARY_PROMPT,
    existing_summary_prompt=DEFAULT_EXISTING_SUMMARY_PROMPT,
)
messags_after_summarization = summarization_result.messages

# If there are exactly two system messages after summarization, convert the second one to an AIMessage
system_message_indices = [i for i, msg in enumerate(messags_after_summarization) if isinstance(msg, SystemMessage)]
if len(system_message_indices) == 2:
    print(system_message_indices)
    second_system_idx = system_message_indices[1]
    messags_after_summarization[second_system_idx] = AIMessage(content=messags_after_summarization[second_system_idx].content)
    # Insert a HumanMessage after the second system message using the first message from state
    # human_msg = HumanMessage(content="Look at the summary and the conversation below and decide what to do next.")
    # messags_after_summarization.insert(second_system_idx, human_msg)
    print(messags_after_summarization)
await asyncio.sleep(10)
response = await llm_tools.ainvoke(messags_after_summarization)
state_update = {"messages": [response]}
if summarization_result.running_summary:
    state_update["summary"] = summarization_result.running_summary

# Return the response as a message
return state_update`

2026-04-11T20:20:44.443753Z [info     ] Retrying task llm_with_tools after 1.15 seconds (attempt 1) after ResponseError Service Temporarily Unavailable (status code: 503) [langgraph.pregel._retry] api_variant=local_dev assistant_id=fe096781-5601-53d2-b2f6-0d3403f7e9ca graph_id=agent langgraph_api_version=0.7.56 request_id=bd85cd81-e24d-4e35-adf2-a9eecd822482 run_attempt=1 run_id=019d7e32-29ee-7103-9a76-8df5d8300795 thread_id=2a49f20a-8cf8-4530-aa65-232198cd0833 thread_name=MainThread
Traceback (most recent call last):
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langgraph\pregel\_retry.py", line 211, in arun_with_retry
    return await task.proc.ainvoke(task.input, config)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langgraph\_internal\_runnable.py", line 705, in ainvoke
    input = await asyncio.create_task(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langgraph\_internal\_runnable.py", line 473, in ainvoke
    ret = await self.afunc(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\AI\basic-agent\basic_deep_agent\src\AI_Nodes\nodes.py", line 93, in llm_with_tools
    response = await llm_tools.ainvoke(messags_after_summarization)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_core\runnables\base.py", line 5708, in ainvoke
    return await self.bound.ainvoke(
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_core\language_models\chat_models.py", line 425, in ainvoke
    llm_result = await self.agenerate_prompt(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1134, in agenerate_prompt
    return await self.agenerate(
           ^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1092, in agenerate
    raise exceptions[0]
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1318, in _agenerate_with_cache
    async for chunk in self._astream(messages, stop=stop, **kwargs):
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_ollama\chat_models.py", line 1193, in _astream
    async for chunk in self._aiterate_over_stream(messages, stop, **kwargs):
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_ollama\chat_models.py", line 1131, in _aiterate_over_stream
    async for stream_resp in self._acreate_chat_stream(messages, stop, **kwargs):
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\langchain_ollama\chat_models.py", line 937, in _acreate_chat_stream
    async for part in await self._async_client.chat(**chat_params):
  File "C:\Users\aravi\AppData\Local\Programs\Python\Python312\Lib\site-packages\ollama\_client.py", line 741, in inner
    raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: Service Temporarily Unavailable (status code: 503)
During task with name 'llm_with_tools' and id 'fa2904e7-60e4-5492-37ff-aec55365e083'
sleeping for 60 seconds before retrying.