Confirm this is an issue with the Python library and not an underlying OpenAI API
Describe the bug
When using Responses API to do an MCP call, the Response.output field will contain an openai.types.responses.response_output_item.McpCall type. This type has a status field.
When adding this same McpCall object into the input field of a new Responses call, previously there was no issue. Now, it fails with input validation:
{'error': {'message': "Unknown parameter: 'input[2].status'.", 'type': 'invalid_request_error', 'param': 'input[2].status', 'code': 'unknown_parameter'}}
The field status of McpCall is not accepted. Thats because its not in the data model for openai.types.responses.response_output_item.McpCall.
So, why is status being added to the openai.types.responses.response_output_item.McpCall output, and why previously was this ok to use and now its not. Im talking a difference between 2025/09/25 (working) and 2025/09/29 (not working)
Removing status field from the McpCall and then sending the same request does work ✅
To Reproduce
- Do an MCP call
- Add the MCP call response output item to the
input of a second call
- This second call will fail (see code snippet to reproduce
Code snippets
from openai import OpenAI
client = OpenAI()
input = [{"role":"user","content":"How does tiktoken work?"}]
response_tiktoken=client.responses.create(tools=[{
"type": "mcp",
"server_label": "gitmcp",
"server_url": "https://gitmcp.io/openai/tiktoken",
"allowed_tools": ["search_tiktoken_documentation", "fetch_tiktoken_documentation"],
"require_approval": "never"
}],
input=input,
model="gpt-4o-mini")
tiktoken_mcp_call_outputs = [i for i in response_tiktoken.output if i.type == "mcp_call"]
new_input = input + tiktoken_mcp_call_outputs + [{"role":"user","content":"What did your previous message say?"}]
# this will fail due to `status` in the mcp call
response_tiktoken=client.responses.create(tools=[{
"type": "mcp",
"server_label": "gitmcp",
"server_url": "https://gitmcp.io/openai/tiktoken",
"allowed_tools": ["search_tiktoken_documentation", "fetch_tiktoken_documentation"],
"require_approval": "never"
}],
input=new_input,
model="gpt-4o-mini")
OS
macOS
Python version
3.12
Library version
openai v1.109.0
Confirm this is an issue with the Python library and not an underlying OpenAI API
Describe the bug
When using Responses API to do an MCP call, the
Response.outputfield will contain anopenai.types.responses.response_output_item.McpCalltype. This type has astatusfield.When adding this same
McpCallobject into theinputfield of a new Responses call, previously there was no issue. Now, it fails with input validation:The field
statusofMcpCallis not accepted. Thats because its not in the data model foropenai.types.responses.response_output_item.McpCall.So, why is
statusbeing added to theopenai.types.responses.response_output_item.McpCalloutput, and why previously was this ok to use and now its not. Im talking a difference between 2025/09/25 (working) and 2025/09/29 (not working)Removing
statusfield from theMcpCalland then sending the same request does work ✅To Reproduce
inputof a second callCode snippets
OS
macOS
Python version
3.12
Library version
openai v1.109.0