llama-stack-mirror/tests/verifications/test_results/meta_reference.json
ehhuang 0ed41aafbf
test: add multi_image test (#1972)
# What does this PR do?


## Test Plan
pytest tests/verifications/openai_api/test_chat_completion.py --provider
openai -k 'test_chat_multiple_images'
2025-04-17 12:51:42 -07:00

1097 lines
35 KiB
JSON

{
"created": 1744918847.712677,
"duration": 215.2132911682129,
"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": 0.09800294879823923,
"outcome": "passed"
},
"call": {
"duration": 4.066351721994579,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025077443569898605,
"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": 0.07197055127471685,
"outcome": "passed"
},
"call": {
"duration": 1.1918699434027076,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027959980070590973,
"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": 0.07294174749404192,
"outcome": "passed"
},
"call": {
"duration": 2.027987685985863,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026049185544252396,
"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": 0.0741243390366435,
"outcome": "passed"
},
"call": {
"duration": 1.2185465842485428,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002712178975343704,
"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": 0.07473955396562815,
"outcome": "passed"
},
"call": {
"duration": 10.396870554424822,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025566015392541885,
"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": 0.07153997663408518,
"outcome": "passed"
},
"call": {
"duration": 10.59731453191489,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002689240500330925,
"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": 0.07629724312573671,
"outcome": "passed"
},
"call": {
"duration": 5.293915126472712,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002626115456223488,
"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": 0.07231003511697054,
"outcome": "passed"
},
"call": {
"duration": 19.020215207710862,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025262776762247086,
"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": 0.07291634101420641,
"outcome": "passed"
},
"call": {
"duration": 6.105666604824364,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027642492204904556,
"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": 0.07050449773669243,
"outcome": "passed"
},
"call": {
"duration": 19.080777555704117,
"outcome": "passed"
},
"teardown": {
"duration": 0.000232757069170475,
"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": 0.07927203364670277,
"outcome": "passed"
},
"call": {
"duration": 0.7760327504947782,
"outcome": "passed"
},
"teardown": {
"duration": 0.00024862587451934814,
"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": 0.07514432724565268,
"outcome": "passed"
},
"call": {
"duration": 0.7971448050811887,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002687377855181694,
"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": 0.07167623657733202,
"outcome": "passed"
},
"call": {
"duration": 0.6906132427975535,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003270544111728668,
"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": 0.0725558316335082,
"outcome": "passed"
},
"call": {
"duration": 0.9245227407664061,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002602478489279747,
"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": 0.07299680262804031,
"outcome": "passed"
},
"call": {
"duration": 31.90802155341953,
"outcome": "passed"
},
"teardown": {
"duration": 0.00023696757853031158,
"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": 0.07331038825213909,
"outcome": "passed"
},
"call": {
"duration": 39.341348845511675,
"outcome": "passed"
},
"teardown": {
"duration": 0.00022847391664981842,
"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": 0.10512833576649427,
"outcome": "passed"
},
"call": {
"duration": 2.9590865215286613,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002405792474746704,
"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": 0.07294358871877193,
"outcome": "passed"
},
"call": {
"duration": 1.7672317335382104,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003217160701751709,
"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": 0.11179900728166103,
"outcome": "passed"
},
"call": {
"duration": 2.411543940193951,
"outcome": "passed"
},
"teardown": {
"duration": 0.00023025460541248322,
"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": 0.07234534807503223,
"outcome": "passed"
},
"call": {
"duration": 4.438527720049024,
"outcome": "passed"
},
"teardown": {
"duration": 0.00028106197714805603,
"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": 0.06979168020188808,
"outcome": "passed"
},
"call": {
"duration": 3.186668715439737,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002599591389298439,
"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": 0.07083943020552397,
"outcome": "passed"
},
"call": {
"duration": 2.31697681453079,
"outcome": "passed"
},
"teardown": {
"duration": 0.00029378384351730347,
"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": 0.07374998275190592,
"outcome": "passed"
},
"call": {
"duration": 1.7863417640328407,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025129225105047226,
"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": 0.07009322382509708,
"outcome": "passed"
},
"call": {
"duration": 2.248749589547515,
"outcome": "passed"
},
"teardown": {
"duration": 0.00022566411644220352,
"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": 0.10290939453989267,
"outcome": "passed"
},
"call": {
"duration": 4.644147016108036,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002319561317563057,
"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": 0.07125874608755112,
"outcome": "passed"
},
"call": {
"duration": 3.2340452317148447,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002202410250902176,
"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": 0.07085523661226034,
"outcome": "passed"
},
"call": {
"duration": 17.7453119084239,
"outcome": "passed"
},
"teardown": {
"duration": 0.00037308502942323685,
"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": 0.07670701760798693,
"outcome": "passed"
},
"call": {
"duration": 12.663874679245055,
"outcome": "passed"
},
"teardown": {
"duration": 0.0008251797407865524,
"outcome": "passed"
}
}
],
"run_timestamp": 1744918631
}