phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 01:48:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove unreliable parallel tool calls tests

Browse source 
Removed tests for parallel tool calls due to reliability issues.
This commit is contained in:
Anastas Stoyanovsky 2025-11-14 14:42:14 -05:00
parent dfc62a2b61
commit 9bb0e16908
1 changed files with 0 additions and 93 deletions
Download patch file Download diff file Expand all files Collapse all files

93
tests/integration/agents/test_openai_responses.py
View file

@ -682,96 +682,3 @@ def test_max_tool_calls_with_builtin_tools(openai_client, client_with_models, te
# Verify we have a valid max_tool_calls field
assert response_3.max_tool_calls == max_tool_calls[1]
@pytest.mark.skip(reason="Tool calling is not reliable.")
def test_parallel_tool_calls_true(openai_client, client_with_models, text_model_id):
"""Test handling of max_tool_calls with function tools in responses."""
if isinstance(client_with_models, LlamaStackAsLibraryClient):
pytest.skip("OpenAI responses are not supported when testing with library client yet.")
client = openai_client
parallel_tool_calls = True
tools = [
{
"type": "function",
"name": "get_weather",
"description": "Get weather information for a specified location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name (e.g., 'New York', 'London')",
},
},
},
}
]
# First create a response that triggers function tools
response = client.responses.create(
model=text_model_id,
input="Get the weather in New York and in Paris",
tools=tools,
stream=False,
parallel_tool_calls=parallel_tool_calls,
)
# Verify we got two function calls and that the max_tool_calls do not affect function tools
assert len(response.output) == 2
assert response.output[0].type == "function_call"
assert response.output[0].name == "get_weather"
assert response.output[0].status == "completed"
assert response.output[1].type == "function_call"
assert response.output[1].name == "get_weather"
assert response.output[0].status == "completed"
# Verify we have a valid max_tool_calls field
assert response.parallel_tool_calls == parallel_tool_calls
@pytest.mark.skip(reason="Tool calling is not reliable.")
def test_parallel_tool_calls_false(openai_client, client_with_models, text_model_id):
"""Test handling of max_tool_calls with function tools in responses."""
if isinstance(client_with_models, LlamaStackAsLibraryClient):
pytest.skip("OpenAI responses are not supported when testing with library client yet.")
client = openai_client
parallel_tool_calls = False
tools = [
{
"type": "function",
"name": "get_weather",
"description": "Get weather information for a specified location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name (e.g., 'New York', 'London')",
},
},
},
}
]
# First create a response that triggers function tools
response = client.responses.create(
model=text_model_id,
input="Get the weather in New York and in Paris",
tools=tools,
stream=False,
parallel_tool_calls=parallel_tool_calls,
)
# Verify we got two function calls and that the max_tool_calls do not affect function tools
assert len(response.output) == 1
assert response.output[0].type == "function_call"
assert response.output[0].name == "get_weather"
assert response.output[0].status == "completed"
# Verify we have a valid max_tool_calls field
assert response.parallel_tool_calls == parallel_tool_calls