Why AgentExecutor chain not return final results?

[srn-source]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain.agents import AgentExecutor, create_tool_calling_agent

from langchain.prompts import ChatPromptTemplate
from langchain_core.prompts import MessagesPlaceholder

tools = [
         company_information,
         last_dividend_and_earnings_date,
         stock_splits_history,
         summary_of_mutual_fund_holders,
         summary_of_institutional_holders, 
         stock_grade_updrages_downgrades,
         stock_news
]

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are an expert in composing functions.",
        ),
        MessagesPlaceholder(variable_name="messages"),
        MessagesPlaceholder(variable_name="agent_scratchpad"),
    ]
)

finance_agent = create_tool_calling_agent(llama3, tools, prompt)
finance_agent_executor = AgentExecutor(agent=finance_agent, tools=tools,use_function_response=True,  verbose=True, handle_parsing_errors=True, max_iterations=10)

from langchain_core.messages import HumanMessage

resp = finance_agent_executor.invoke({"messages": [HumanMessage(content="What is address of microsoft?")]})

Description

Entering new AgentExecutor chain...
{
"tool_calls": [
{"name": "company_information", "arguments": {"ticker": "MSFT"}}
]
}

Finished chain.

Above is results that i dont get final answer they just return tool call not finalize text results like "company address is ......"
BTW i use my own model
with chat template llama3
Role: system
Role: user
Role: assistance
Role: tool

System Info

pip install langchain