fix: don't pass default response format in Responses (#3614)

# What does this PR do?
Fireworks doesn't allow repsonse_format with tool use. The default
response format is 'text' anyway, so we can safely omit.


## Test Plan
Below script failed without the change, runs after.

```
#!/usr/bin/env python3
"""
Script to test Responses API with kubernetes-mcp-server.

This script:
1. Connects to the llama stack server
2. Uses the Responses API with MCP tools
3. Asks for the list of Kubernetes namespaces using the kubernetes-mcp-server
"""

import json

from openai import OpenAI

# Connect to the llama stack server
base_url = "http://localhost:8321/v1"
client = OpenAI(base_url=base_url, api_key="fake")

# Define the MCP tool pointing to the kubernetes-mcp-server
# The kubernetes-mcp-server is running on port 3000 with SSE endpoint at /sse
mcp_server_url = "http://localhost:3000/sse"

tools = [
    {
        "type": "mcp",
        "server_label": "k8s",
        "server_url": mcp_server_url,
    }
]

# Create a response request asking for k8s namespaces
print("Sending request to list Kubernetes namespaces...")
print(f"Using MCP server at: {mcp_server_url}")
print("Available tools will be listed automatically by the MCP server.")
print()

response = client.responses.create(
    # model="meta-llama/Llama-3.2-3B-Instruct",  # Using the vllm model
    model="fireworks/accounts/fireworks/models/llama4-scout-instruct-basic",
    # model="openai/gpt-4o",
    input="what are all the Kubernetes namespaces? Use tool call to `namespaces_list`. make sure to adhere to the tool calling format UNDER ALL CIRCUMSTANCES.",
    tools=tools,
    stream=False,
)

print("\n" + "=" * 80)
print("RESPONSE OUTPUT:")
print("=" * 80)

# Print the output
for i, output in enumerate(response.output):
    print(f"\n[Output {i + 1}] Type: {output.type}")
    if output.type == "mcp_list_tools":
        print(f"  Server: {output.server_label}")
        print(f"  Tools available: {[t.name for t in output.tools]}")
    elif output.type == "mcp_call":
        print(f"  Tool called: {output.name}")
        print(f"  Arguments: {output.arguments}")
        print(f"  Result: {output.output}")
        if output.error:
            print(f"  Error: {output.error}")
    elif output.type == "message":
        print(f"  Role: {output.role}")
        print(f"  Content: {output.content}")

print("\n" + "=" * 80)
print("FINAL RESPONSE TEXT:")
print("=" * 80)
print(response.output_text)
```
This commit is contained in:
ehhuang 2025-09-30 14:52:24 -07:00 committed by GitHub
parent d350e3662b
commit ac7c35fbe6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 7573 additions and 89 deletions

View file

@ -37,7 +37,6 @@ from llama_stack.apis.inference import (
OpenAIJSONSchema,
OpenAIResponseFormatJSONObject,
OpenAIResponseFormatJSONSchema,
OpenAIResponseFormatText,
OpenAIUserMessageParam,
)
from llama_stack.apis.tools.tools import Tool, ToolGroups, ToolInvocationResult, ToolParameter, ToolRuntime
@ -148,7 +147,7 @@ async def test_create_openai_response_with_string_input(openai_responses_impl, m
mock_inference_api.openai_chat_completion.assert_called_once_with(
model=model,
messages=[OpenAIUserMessageParam(role="user", content="What is the capital of Ireland?", name=None)],
response_format=OpenAIResponseFormatText(),
response_format=None,
tools=None,
stream=True,
temperature=0.1,
@ -823,16 +822,16 @@ async def test_store_response_uses_rehydrated_input_with_previous_response(
@pytest.mark.parametrize(
"text_format, response_format",
[
(OpenAIResponseText(format=OpenAIResponseTextFormat(type="text")), OpenAIResponseFormatText()),
(OpenAIResponseText(format=OpenAIResponseTextFormat(type="text")), None),
(
OpenAIResponseText(format=OpenAIResponseTextFormat(name="Test", schema={"foo": "bar"}, type="json_schema")),
OpenAIResponseFormatJSONSchema(json_schema=OpenAIJSONSchema(name="Test", schema={"foo": "bar"})),
),
(OpenAIResponseText(format=OpenAIResponseTextFormat(type="json_object")), OpenAIResponseFormatJSONObject()),
# ensure text param with no format specified defaults to text
(OpenAIResponseText(format=None), OpenAIResponseFormatText()),
# ensure text param of None defaults to text
(None, OpenAIResponseFormatText()),
# ensure text param with no format specified defaults to None
(OpenAIResponseText(format=None), None),
# ensure text param of None defaults to None
(None, None),
],
)
async def test_create_openai_response_with_text_format(
@ -855,7 +854,6 @@ async def test_create_openai_response_with_text_format(
# Verify
first_call = mock_inference_api.openai_chat_completion.call_args_list[0]
assert first_call.kwargs["messages"][0].content == input_text
assert first_call.kwargs["response_format"] is not None
assert first_call.kwargs["response_format"] == response_format