core: `missing_required_parameter` when using LangGraph to pass multimodal data to models

Checked other resources

• I added a very descriptive title to this issue.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Example Code

Hi all,

 messages = prompt + state["messages"]
 chat = ChatPromptTemplate.from_messages(messages)
logger.debug("-------------------------------------------------------------------------------->> invoking LLM with config")
logger.debug(f"{chat}")
logger.debug("-------------------------------------------------------------------------------->> invoking LLM...")
response = await model.ainvoke(chat.format_prompt(), config)

Error Message and Stack Trace (if applicable)

this outputs:

== APP == -------------------------------------------------------------------------------->> invoking LLM with config
== APP == input_variables=[] input_types={} partial_variables={} messages=[SystemMessage(content="You are a concierge agent. You are very helpful and friendly. You are very polite and respectful. You are always ready to help.\n\ncurrent date/time: 2025-06-05 19:32:40\n\nuser context: {'id': '123123123', 'name': 'Bruno Figueiredo', 'avatar': ''}", additional_kwargs={}, response_metadata={}), HumanMessage(content='olá', additional_kwargs={}, response_metadata={}, id='8fa5db18-69b0-4085-9d4e-aa16847da243'), AIMessage(content='Olá, Bruno! 😊 Como posso ajudar você hoje?', additional_kwargs={}, response_metadata={'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-11-20', 'system_fingerprint': 'fp_ee1d74bde0'}, id='run-2df83ba9-a843-4029-a020-0d41465fddf3'), HumanMessage(content=[{'type': 'text', 'text': 'resume'}, {'type': 'file', 'source_type': 'url', 'url': 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf'}], additional_kwargs={}, response_metadata={}, id='363b871a-d9bc-4f40-ab56-5138486e7f07')]
== APP == -------------------------------------------------------------------------------->> invoking LLM...
== APP == Error invoking model: Error code: 400 - {'error': {'message': "Missing required parameter: 'messages[3].content[1].file'.", 'type': 'invalid_request_error', 'param': 'messages[3].content[1].file', 'code': 'missing_required_parameter'}}

Description

Hi all,

I have a langgraph agent with several nodes and I'm calling the graph via agent.astream_events(**kwargs, version="v2").

Tested with GPT4o and gemini-1.5-flash

If I use an image the code works well

HumanMessage(
                    content=[
                        {"type": "text", "text": user_input.message},
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": f"data:{user_input.file_type};base64,{user_input.file}"
                            },
                        }
                    ]
                )

but if I use a file I get the error above

 HumanMessage(
                        content=[
                            {"type": "text", "text": user_input.message},
                            {
                                "type": "file",
                                "source_type": "url",
                                "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
                            },
                        ]
                    )

Any thoughs? thanks

System Info

== APP == == APP == System Information == APP == ------------------ == APP == > OS: Linux == APP == > OS Version: #1 SMP PREEMPT_DYNAMIC Mon Apr 21 17:08:54 UTC 2025 == APP == > Python Version: 3.12.3 (main, Feb 4 2025, 14:48:35) [GCC 13.3.0] == APP == == APP == Package Information == APP == ------------------- == APP == > langchain_core: 0.3.48 == APP == > langchain: 0.3.15 == APP == > langchain_community: 0.3.15 == APP == > langsmith: 0.2.11 == APP == > langchain_chroma: 0.1.4 == APP == > langchain_google_genai: 2.1.1 == APP == > langchain_groq: 0.3.1 == APP == > langchain_mcp_adapters: 0.0.5 == APP == > langchain_ollama: 0.3.0 == APP == > langchain_openai: 0.2.14 == APP == > langchain_postgres: 0.0.13 == APP == > langchain_text_splitters: 0.3.5 == APP == > langgraph_sdk: 0.1.51 == APP == == APP == Optional packages not installed == APP == ------------------------------- == APP == > langserve == APP == == APP == Other Dependencies == APP == ------------------ == APP == > aiohttp: 3.11.11 == APP == > async-timeout: Installed. No version info available. == APP == > chromadb: 0.5.0 == APP == > dataclasses-json: 0.6.7 == APP == > fastapi: 0.115.6 == APP == > filetype: 1.2.0 == APP == > google-ai-generativelanguage: 0.6.17 == APP == > groq<1,>=0.4.1: Installed. No version info available. == APP == > httpx: 0.28.1 == APP == > httpx-sse: 0.4.0 == APP == > jsonpatch<2.0,>=1.33: Installed. No version info available. == APP == > langchain-core<0.4,>=0.3.36: Installed. No version info available. == APP == > langchain-core<1.0.0,>=0.3.47: Installed. No version info available. == APP == > langsmith-pyo3: Installed. No version info available. == APP == > langsmith<0.4,>=0.1.125: Installed. No version info available. == APP == > mcp<1.5,>=1.4.1: Installed. No version info available. == APP == > numpy: 1.26.4 == APP == > ollama<1,>=0.4.4: Installed. No version info available. == APP == > openai: 1.59.9 == APP == > orjson: 3.10.15 == APP == > packaging<25,>=23.2: Installed. No version info available. == APP == > pgvector: 0.2.5 == APP == > psycopg: 3.2.6 == APP == > psycopg-pool: 3.2.6 == APP == > pydantic: 2.10.5 == APP == > pydantic-settings: 2.7.1 == APP == > pydantic<3.0.0,>=2.5.2;: Installed. No version info available. == APP == > pydantic<3.0.0,>=2.7.4;: Installed. No version info available. == APP == > PyYAML: 6.0.2 == APP == > PyYAML>=5.3: Installed. No version info available. == APP == > requests: 2.32.3 == APP == > requests-toolbelt: 1.0.0 == APP == > SQLAlchemy: 2.0.37 == APP == > sqlalchemy: 2.0.37 == APP == > tenacity: 9.0.0 == APP == > tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available. == APP == > tiktoken: 0.8.0 == APP == > typing-extensions>=4.7: Installed. No version info available. == APP == > zstandard: Installed. No version info available.