phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 06:01:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/tests/verifications/test_results/meta_reference.json
Eric Huang d5abe2ec2e tests: add multi_image test 
# What does this PR do?


## Test Plan
2025-04-17 11:52:20 -07:00

1097 lines
35 KiB
JSON
Raw Blame History

{
"created": 1744915514.208135,
"duration": 202.18266344070435,
"exitcode": 0,
"root": "/home/erichuang/llama-stack",
"environment": {},
"summary": {
"passed": 28,
"total": 28,
"collected": 28
},
"collectors": [
{
"nodeid": "",
"outcome": "passed",
"result": [
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py",
"type": "Module"
}
]
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py",
"outcome": "passed",
"result": [
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-earth]",
"type": "Function",
"lineno": 95
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn]",
"type": "Function",
"lineno": 95
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-earth]",
"type": "Function",
"lineno": 114
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn]",
"type": "Function",
"lineno": 114
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 138
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 157
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar]",
"type": "Function",
"lineno": 181
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-math]",
"type": "Function",
"lineno": 181
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar]",
"type": "Function",
"lineno": 204
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-math]",
"type": "Function",
"lineno": 204
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 226
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 250
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 278
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 302
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 329
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"type": "Function",
"lineno": 352
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool]",
"type": "Function",
"lineno": 380
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text]",
"type": "Function",
"lineno": 380
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool]",
"type": "Function",
"lineno": 380
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool]",
"type": "Function",
"lineno": 380
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool]",
"type": "Function",
"lineno": 380
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool]",
"type": "Function",
"lineno": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text]",
"type": "Function",
"lineno": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool]",
"type": "Function",
"lineno": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool]",
"type": "Function",
"lineno": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool]",
"type": "Function",
"lineno": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=False]",
"type": "Function",
"lineno": 554
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=True]",
"type": "Function",
"lineno": 554
}
]
}
],
"tests": [
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-earth]",
"lineno": 95,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-earth]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-earth",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "earth"
},
"setup": {
"duration": 0.09510238654911518,
"outcome": "passed"
},
"call": {
"duration": 2.7976166242733598,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002804817631840706,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn]",
"lineno": 95,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "saturn"
},
"setup": {
"duration": 0.0735457269474864,
"outcome": "passed"
},
"call": {
"duration": 1.0852967854589224,
"outcome": "passed"
},
"teardown": {
"duration": 0.00029948819428682327,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-earth]",
"lineno": 114,
"outcome": "passed",
"keywords": [
"test_chat_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-earth]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-earth",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "earth"
},
"setup": {
"duration": 0.07200248818844557,
"outcome": "passed"
},
"call": {
"duration": 0.41483108792454004,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002880822867155075,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn]",
"lineno": 114,
"outcome": "passed",
"keywords": [
"test_chat_streaming_basic[meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-saturn",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "saturn"
},
"setup": {
"duration": 0.07424226123839617,
"outcome": "passed"
},
"call": {
"duration": 1.1533718826249242,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026405230164527893,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 138,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_image[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07035014033317566,
"outcome": "passed"
},
"call": {
"duration": 11.941276826895773,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002712151035666466,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 157,
"outcome": "passed",
"keywords": [
"test_chat_streaming_image[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.08027863781899214,
"outcome": "passed"
},
"call": {
"duration": 5.189308542758226,
"outcome": "passed"
},
"teardown": {
"duration": 0.000255669467151165,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar]",
"lineno": 181,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "calendar"
},
"setup": {
"duration": 0.07215503882616758,
"outcome": "passed"
},
"call": {
"duration": 7.25669299531728,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002499222755432129,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-math]",
"lineno": 181,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-math]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-math",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "math"
},
"setup": {
"duration": 0.0723958220332861,
"outcome": "passed"
},
"call": {
"duration": 23.26972564868629,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002250121906399727,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar]",
"lineno": 204,
"outcome": "passed",
"keywords": [
"test_chat_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-calendar",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "calendar"
},
"setup": {
"duration": 0.0755303306505084,
"outcome": "passed"
},
"call": {
"duration": 6.047801445238292,
"outcome": "passed"
},
"teardown": {
"duration": 0.00023919064551591873,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-math]",
"lineno": 204,
"outcome": "passed",
"keywords": [
"test_chat_streaming_structured_output[meta-llama/Llama-4-Scout-17B-16E-Instruct-math]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-math",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "math"
},
"setup": {
"duration": 0.07097675651311874,
"outcome": "passed"
},
"call": {
"duration": 26.09199330676347,
"outcome": "passed"
},
"teardown": {
"duration": 0.00032348278909921646,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 226,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07283070310950279,
"outcome": "passed"
},
"call": {
"duration": 0.7768763303756714,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002704216167330742,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 250,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07072548102587461,
"outcome": "passed"
},
"call": {
"duration": 0.7484909351915121,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002851812168955803,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 278,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_choice_required[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07187876384705305,
"outcome": "passed"
},
"call": {
"duration": 0.7497121002525091,
"outcome": "passed"
},
"teardown": {
"duration": 0.00029664672911167145,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 302,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_choice_required[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07151791825890541,
"outcome": "passed"
},
"call": {
"duration": 1.1092564295977354,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002770284190773964,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 329,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_choice_none[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07284159772098064,
"outcome": "passed"
},
"call": {
"duration": 28.572499179281294,
"outcome": "passed"
},
"teardown": {
"duration": 0.00031286943703889847,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"lineno": 352,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_choice_none[meta-llama/Llama-4-Scout-17B-16E-Instruct-case0]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "case0"
},
"setup": {
"duration": 0.07455504685640335,
"outcome": "passed"
},
"call": {
"duration": 27.01730054244399,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002900902181863785,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool]",
"lineno": 380,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "text_then_weather_tool"
},
"setup": {
"duration": 0.10514138638973236,
"outcome": "passed"
},
"call": {
"duration": 2.5916615584865212,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003233887255191803,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text]",
"lineno": 380,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "weather_tool_then_text"
},
"setup": {
"duration": 0.09724622592329979,
"outcome": "passed"
},
"call": {
"duration": 1.6816193973645568,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002651568502187729,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool]",
"lineno": 380,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "add_product_tool"
},
"setup": {
"duration": 0.0717660365626216,
"outcome": "passed"
},
"call": {
"duration": 2.301668006926775,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002871360629796982,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool]",
"lineno": 380,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "get_then_create_event_tool"
},
"setup": {
"duration": 0.07237224746495485,
"outcome": "passed"
},
"call": {
"duration": 4.44710533414036,
"outcome": "passed"
},
"teardown": {
"duration": 0.000309748575091362,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool]",
"lineno": 380,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "compare_monthly_expense_tool"
},
"setup": {
"duration": 0.07419578451663256,
"outcome": "passed"
},
"call": {
"duration": 3.0712353149428964,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003073718398809433,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool]",
"lineno": 471,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-text_then_weather_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "text_then_weather_tool"
},
"setup": {
"duration": 0.07015236373990774,
"outcome": "passed"
},
"call": {
"duration": 2.4258732767775655,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002886578440666199,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text]",
"lineno": 471,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-weather_tool_then_text",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "weather_tool_then_text"
},
"setup": {
"duration": 0.07009198423475027,
"outcome": "passed"
},
"call": {
"duration": 1.7146461214870214,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003043804317712784,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool]",
"lineno": 471,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-add_product_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "add_product_tool"
},
"setup": {
"duration": 0.07378454692661762,
"outcome": "passed"
},
"call": {
"duration": 2.3185672890394926,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002978481352329254,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool]",
"lineno": 471,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-get_then_create_event_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "get_then_create_event_tool"
},
"setup": {
"duration": 0.07212705258280039,
"outcome": "passed"
},
"call": {
"duration": 4.408322776667774,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003781057894229889,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool]",
"lineno": 471,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-compare_monthly_expense_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "compare_monthly_expense_tool"
},
"setup": {
"duration": 0.07353641279041767,
"outcome": "passed"
},
"call": {
"duration": 3.327573754824698,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003117518499493599,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=False]",
"lineno": 554,
"outcome": "passed",
"keywords": [
"test_chat_multi_turn_multiple_images[meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=False]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=False",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "stream=False"
},
"setup": {
"duration": 0.07416135538369417,
"outcome": "passed"
},
"call": {
"duration": 17.42448517587036,
"outcome": "passed"
},
"teardown": {
"duration": 0.00031717773526906967,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=True]",
"lineno": 554,
"outcome": "passed",
"keywords": [
"test_chat_multi_turn_multiple_images[meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=True]",
"parametrize",
"pytestmark",
"meta-llama/Llama-4-Scout-17B-16E-Instruct-stream=True",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"case_id": "stream=True"
},
"setup": {
"duration": 0.07180674187839031,
"outcome": "passed"
},
"call": {
"duration": 9.833569367416203,
"outcome": "passed"
},
"teardown": {
"duration": 0.0012101922184228897,
"outcome": "passed"
}
}
],
"run_timestamp": 1744915311
}
Reference in a new issue View git blame Copy permalink