Agent Executor Submits Tool Ouputs Twice (Or shows same behaviour)

Checked other resources

[X] I added a very descriptive title to this issue.
[X] I searched the LangChain documentation with the integrated search.
[X] I used the GitHub search to find a similar question and didn't find it.
[X] I am sure that this is a bug in LangChain rather than my code.
[X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

gpt4o = ChatOpenAI(
    model="gpt-4o",
    streaming=True,
    extra_body={
        "response_format": {
            "type": "json_schema",
            "json_schema": {
                "name": "response",
                "strict": True,
                "schema": responseSchema
            }
        }
    },
    temperature=0.6,)
currentModel = gpt4o
showImageTool = ShowImageTool()
tools = [
    showImageTool
]

agent = create_tool_calling_agent(
  llm=toolCallingModel,
  tools=tools,
  prompt=prompt
)
agentExecutor = AgentExecutor(
    agent=agent,
    tools=tools,
    return_intermediate_steps=True,
    verbose=True
)

Error Message and Stack Trace (if applicable)

No response

Description

I have a AgentExecutor with only 1 tool call, the returned info from tool is not important so I am only returning "tool_done" from the tool execution.

After the execution done, tool outputs get submitted to the model and new step output starts to come, but at some point, model restarts to produce new output (like tool is resubmitted)

Verbose output is as follows:

Invoking: `show_image` with `{'imageId': 'test-id'}`
responded: {"content":["<some_content_array>"]}

image_shown: test-id{"content":["some_content_array", "after_image_shown"]}
{"content":["<some_new_content>"]}

The model has structured output, so output with this type breaks the structure. (The new content does not comes with new chat message, it just continues to stream like that)

I tried same structure and function in openAI playground, it works correctly in there, whether it calls the tool at the start, middle or end.

System Info

System Information
------------------
> OS:  Darwin
> OS Version:  Darwin Kernel Version 24.0.0: Mon Aug 12 20:52:18 PDT 2024; root:xnu-11215.1.10~2/RELEASE_ARM64_T8122
> Python Version:  3.11.10 (main, Sep  7 2024, 01:03:31) [Clang 15.0.0 (clang-1500.3.9.4)]

Package Information
-------------------
> langchain_core: 0.3.10
> langchain: 0.3.3
> langchain_community: 0.3.2
> langsmith: 0.1.133
> langchain_astradb: 0.5.0
> langchain_cli: 0.0.31
> langchain_openai: 0.2.2
> langchain_text_splitters: 0.3.0
> langchain_unstructured: 0.1.5
> langserve: 0.3.0

Optional packages not installed
-------------------------------
> langgraph

Other Dependencies
------------------
> aiohttp: 3.10.9
> astrapy: 1.5.2
> async-timeout: Installed. No version info available.
> dataclasses-json: 0.6.7
> fastapi: 0.112.4
> gitpython: 3.1.43
> gritql: 0.1.5
> httpx: 0.27.2
> jsonpatch: 1.33
> langserve[all]: Installed. No version info available.
> numpy: 1.26.4
> openai: 1.51.2
> orjson: 3.10.7
> packaging: 24.1
> pydantic: 2.9.2
> pydantic-settings: 2.5.2
> PyYAML: 6.0.2
> requests: 2.31.0
> requests-toolbelt: 1.0.0
> SQLAlchemy: 2.0.35
> sse-starlette: 1.8.2
> tenacity: 8.5.0
> tiktoken: 0.8.0
> tomlkit: 0.12.5
> typer[all]: Installed. No version info available.
> typing-extensions: 4.12.2
> unstructured-client: 0.25.9
> unstructured[all-docs]: Installed. No version info available.
> uvicorn: 0.23.2

langchain-ai / langchain