phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 21:21:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/tests/verifications/test_results/openai.json
ehhuang 8bd6665775
chore(verification): update README and reorganize generate_report.py (#1978) 
# What does this PR do?


## Test Plan
uv run --with-editable ".[dev]" python
tests/verifications/generate_report.py --run-tests
2025-04-17 10:41:22 -07:00

2011 lines
59 KiB
JSON
Raw Blame History

{
"created": 1744841456.846108,
"duration": 94.55667495727539,
"exitcode": 0,
"root": "/Users/erichuang/projects/llama-stack",
"environment": {},
"summary": {
"passed": 52,
"total": 52,
"collected": 52
},
"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[gpt-4o-earth]",
"type": "Function",
"lineno": 74
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-saturn]",
"type": "Function",
"lineno": 74
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-earth]",
"type": "Function",
"lineno": 74
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
"type": "Function",
"lineno": 74
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-earth]",
"type": "Function",
"lineno": 93
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-saturn]",
"type": "Function",
"lineno": 93
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-earth]",
"type": "Function",
"lineno": 93
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-saturn]",
"type": "Function",
"lineno": 93
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-case0]",
"type": "Function",
"lineno": 117
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 117
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-case0]",
"type": "Function",
"lineno": 136
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 136
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-calendar]",
"type": "Function",
"lineno": 160
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-math]",
"type": "Function",
"lineno": 160
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
"type": "Function",
"lineno": 160
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
"type": "Function",
"lineno": 160
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-calendar]",
"type": "Function",
"lineno": 183
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-math]",
"type": "Function",
"lineno": 183
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
"type": "Function",
"lineno": 183
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-math]",
"type": "Function",
"lineno": 183
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-case0]",
"type": "Function",
"lineno": 205
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 205
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-case0]",
"type": "Function",
"lineno": 229
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 229
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-case0]",
"type": "Function",
"lineno": 257
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 257
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-case0]",
"type": "Function",
"lineno": 282
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 282
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-case0]",
"type": "Function",
"lineno": 309
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 309
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-case0]",
"type": "Function",
"lineno": 332
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 332
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-text_then_weather_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-weather_tool_then_text]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-get_then_create_event_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-compare_monthly_expense_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-text_then_weather_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-weather_tool_then_text]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-add_product_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-get_then_create_event_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-compare_monthly_expense_tool]",
"type": "Function",
"lineno": 360
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-text_then_weather_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-weather_tool_then_text]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-get_then_create_event_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-compare_monthly_expense_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-text_then_weather_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-weather_tool_then_text]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-add_product_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-get_then_create_event_tool]",
"type": "Function",
"lineno": 451
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-compare_monthly_expense_tool]",
"type": "Function",
"lineno": 451
}
]
}
],
"tests": [
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-earth]",
"lineno": 74,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_basic[gpt-4o-earth]",
"parametrize",
"pytestmark",
"gpt-4o-earth",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "earth"
},
"setup": {
"duration": 0.12443312490358949,
"outcome": "passed"
},
"call": {
"duration": 0.8473757090978324,
"outcome": "passed"
},
"teardown": {
"duration": 0.00016116583719849586,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-saturn]",
"lineno": 74,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_basic[gpt-4o-saturn]",
"parametrize",
"pytestmark",
"gpt-4o-saturn",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "saturn"
},
"setup": {
"duration": 0.006899583851918578,
"outcome": "passed"
},
"call": {
"duration": 0.6270905418787152,
"outcome": "passed"
},
"teardown": {
"duration": 0.00016312487423419952,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-earth]",
"lineno": 74,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_basic[gpt-4o-mini-earth]",
"parametrize",
"pytestmark",
"gpt-4o-mini-earth",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "earth"
},
"setup": {
"duration": 0.006712291855365038,
"outcome": "passed"
},
"call": {
"duration": 0.9687315828632563,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015454203821718693,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
"lineno": 74,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
"parametrize",
"pytestmark",
"gpt-4o-mini-saturn",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "saturn"
},
"setup": {
"duration": 0.01219862513244152,
"outcome": "passed"
},
"call": {
"duration": 0.8335784170776606,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015825009904801846,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-earth]",
"lineno": 93,
"outcome": "passed",
"keywords": [
"test_chat_streaming_basic[gpt-4o-earth]",
"parametrize",
"pytestmark",
"gpt-4o-earth",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "earth"
},
"setup": {
"duration": 0.006971874972805381,
"outcome": "passed"
},
"call": {
"duration": 0.5532776250038296,
"outcome": "passed"
},
"teardown": {
"duration": 0.00017308397218585014,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-saturn]",
"lineno": 93,
"outcome": "passed",
"keywords": [
"test_chat_streaming_basic[gpt-4o-saturn]",
"parametrize",
"pytestmark",
"gpt-4o-saturn",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "saturn"
},
"setup": {
"duration": 0.013978166040033102,
"outcome": "passed"
},
"call": {
"duration": 0.5871057908516377,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015816697850823402,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-earth]",
"lineno": 93,
"outcome": "passed",
"keywords": [
"test_chat_streaming_basic[gpt-4o-mini-earth]",
"parametrize",
"pytestmark",
"gpt-4o-mini-earth",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "earth"
},
"setup": {
"duration": 0.006813500076532364,
"outcome": "passed"
},
"call": {
"duration": 0.4924970408901572,
"outcome": "passed"
},
"teardown": {
"duration": 0.00029533286578953266,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-saturn]",
"lineno": 93,
"outcome": "passed",
"keywords": [
"test_chat_streaming_basic[gpt-4o-mini-saturn]",
"parametrize",
"pytestmark",
"gpt-4o-mini-saturn",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "saturn"
},
"setup": {
"duration": 0.0067986249923706055,
"outcome": "passed"
},
"call": {
"duration": 1.4850703340489417,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002639580052345991,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-case0]",
"lineno": 117,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_image[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.007201374974101782,
"outcome": "passed"
},
"call": {
"duration": 2.7223148751072586,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026712496764957905,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-mini-case0]",
"lineno": 117,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_image[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.0075530000030994415,
"outcome": "passed"
},
"call": {
"duration": 4.295006334083155,
"outcome": "passed"
},
"teardown": {
"duration": 0.00017512496560811996,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-case0]",
"lineno": 136,
"outcome": "passed",
"keywords": [
"test_chat_streaming_image[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.006824542069807649,
"outcome": "passed"
},
"call": {
"duration": 3.3443578749429435,
"outcome": "passed"
},
"teardown": {
"duration": 0.00023495894856750965,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-mini-case0]",
"lineno": 136,
"outcome": "passed",
"keywords": [
"test_chat_streaming_image[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.006994707975536585,
"outcome": "passed"
},
"call": {
"duration": 1.6912214998155832,
"outcome": "passed"
},
"teardown": {
"duration": 0.0007641669362783432,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-calendar]",
"lineno": 160,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_structured_output[gpt-4o-calendar]",
"parametrize",
"pytestmark",
"gpt-4o-calendar",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "calendar"
},
"setup": {
"duration": 0.007816500030457973,
"outcome": "passed"
},
"call": {
"duration": 0.8090797911863774,
"outcome": "passed"
},
"teardown": {
"duration": 0.00017570890486240387,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-math]",
"lineno": 160,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_structured_output[gpt-4o-math]",
"parametrize",
"pytestmark",
"gpt-4o-math",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "math"
},
"setup": {
"duration": 0.007046542130410671,
"outcome": "passed"
},
"call": {
"duration": 4.590162083040923,
"outcome": "passed"
},
"teardown": {
"duration": 0.00016149994917213917,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
"lineno": 160,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
"parametrize",
"pytestmark",
"gpt-4o-mini-calendar",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "calendar"
},
"setup": {
"duration": 0.0068622499238699675,
"outcome": "passed"
},
"call": {
"duration": 0.7782253748737276,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015641585923731327,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
"lineno": 160,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
"parametrize",
"pytestmark",
"gpt-4o-mini-math",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "math"
},
"setup": {
"duration": 0.01584450015798211,
"outcome": "passed"
},
"call": {
"duration": 1.7199794589541852,
"outcome": "passed"
},
"teardown": {
"duration": 0.00016866694204509258,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-calendar]",
"lineno": 183,
"outcome": "passed",
"keywords": [
"test_chat_streaming_structured_output[gpt-4o-calendar]",
"parametrize",
"pytestmark",
"gpt-4o-calendar",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "calendar"
},
"setup": {
"duration": 0.007770000025629997,
"outcome": "passed"
},
"call": {
"duration": 0.6888420830946416,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002853749319911003,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-math]",
"lineno": 183,
"outcome": "passed",
"keywords": [
"test_chat_streaming_structured_output[gpt-4o-math]",
"parametrize",
"pytestmark",
"gpt-4o-math",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "math"
},
"setup": {
"duration": 0.009934042114764452,
"outcome": "passed"
},
"call": {
"duration": 4.339179708156735,
"outcome": "passed"
},
"teardown": {
"duration": 0.00014329212717711926,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
"lineno": 183,
"outcome": "passed",
"keywords": [
"test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
"parametrize",
"pytestmark",
"gpt-4o-mini-calendar",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "calendar"
},
"setup": {
"duration": 0.007238582940772176,
"outcome": "passed"
},
"call": {
"duration": 0.7408282500691712,
"outcome": "passed"
},
"teardown": {
"duration": 0.0004124580882489681,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-math]",
"lineno": 183,
"outcome": "passed",
"keywords": [
"test_chat_streaming_structured_output[gpt-4o-mini-math]",
"parametrize",
"pytestmark",
"gpt-4o-mini-math",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "math"
},
"setup": {
"duration": 0.009300166042521596,
"outcome": "passed"
},
"call": {
"duration": 2.9929484580643475,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002359580248594284,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-case0]",
"lineno": 205,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_calling[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.007114958018064499,
"outcome": "passed"
},
"call": {
"duration": 0.5455114999786019,
"outcome": "passed"
},
"teardown": {
"duration": 0.0001529159490019083,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
"lineno": 205,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.011507000075653195,
"outcome": "passed"
},
"call": {
"duration": 0.9555377080105245,
"outcome": "passed"
},
"teardown": {
"duration": 0.0004787091165781021,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-case0]",
"lineno": 229,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_calling[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.007758707972243428,
"outcome": "passed"
},
"call": {
"duration": 0.6434436670970172,
"outcome": "passed"
},
"teardown": {
"duration": 0.0008757910691201687,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
"lineno": 229,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.009367667138576508,
"outcome": "passed"
},
"call": {
"duration": 0.6695005830843002,
"outcome": "passed"
},
"teardown": {
"duration": 0.00016933400183916092,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-case0]",
"lineno": 257,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_choice_required[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.007463040994480252,
"outcome": "passed"
},
"call": {
"duration": 0.8918469999916852,
"outcome": "passed",
"stdout": "ChatCompletion(id='chatcmpl-BN5FBGF0b1Nv4s3p72ILmlknZuEHk', choices=[Choice(finish_reason='tool_calls', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=[], audio=None, function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_5n6Tl53qYzdf65wPoMisbPBF', function=Function(arguments='{\"location\":\"San Francisco, USA\"}', name='get_weather'), type='function')]))], created=1744841401, model='gpt-4o-2024-08-06', object='chat.completion', service_tier='default', system_fingerprint='fp_f5bdcc3276', usage=CompletionUsage(completion_tokens=18, prompt_tokens=77, total_tokens=95, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0), prompt_tokens_details=PromptTokensDetails(audio_tokens=0, cached_tokens=0)))\n"
},
"teardown": {
"duration": 0.00015658396296203136,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-mini-case0]",
"lineno": 257,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_choice_required[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.018928000004962087,
"outcome": "passed"
},
"call": {
"duration": 0.7251290830317885,
"outcome": "passed",
"stdout": "ChatCompletion(id='chatcmpl-BN5FBpteAqNnvgUbTqVuQRC30StOE', choices=[Choice(finish_reason='tool_calls', index=0, logprobs=None, message=ChatCompletionMessage(content=None, refusal=None, role='assistant', annotations=[], audio=None, function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_WXPajqo5LOCCRn3N6sUoW6OC', function=Function(arguments='{\"location\":\"San Francisco, USA\"}', name='get_weather'), type='function')]))], created=1744841401, model='gpt-4o-mini-2024-07-18', object='chat.completion', service_tier='default', system_fingerprint='fp_44added55e', usage=CompletionUsage(completion_tokens=18, prompt_tokens=77, total_tokens=95, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0), prompt_tokens_details=PromptTokensDetails(audio_tokens=0, cached_tokens=0)))\n"
},
"teardown": {
"duration": 0.0008977497927844524,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-case0]",
"lineno": 282,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_choice_required[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.007159708067774773,
"outcome": "passed"
},
"call": {
"duration": 0.6681597500573844,
"outcome": "passed"
},
"teardown": {
"duration": 0.0010218329261988401,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-mini-case0]",
"lineno": 282,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_choice_required[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.006946499925106764,
"outcome": "passed"
},
"call": {
"duration": 0.564959250157699,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025266711600124836,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-case0]",
"lineno": 309,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_choice_none[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.008796625072136521,
"outcome": "passed"
},
"call": {
"duration": 0.5506484580691904,
"outcome": "passed"
},
"teardown": {
"duration": 0.0006776249501854181,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-mini-case0]",
"lineno": 309,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_tool_choice_none[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.008791540982201695,
"outcome": "passed"
},
"call": {
"duration": 0.5648198751732707,
"outcome": "passed"
},
"teardown": {
"duration": 0.00017616688273847103,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-case0]",
"lineno": 332,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_choice_none[gpt-4o-case0]",
"parametrize",
"pytestmark",
"gpt-4o-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "case0"
},
"setup": {
"duration": 0.0071877078153193,
"outcome": "passed"
},
"call": {
"duration": 1.0776563328690827,
"outcome": "passed"
},
"teardown": {
"duration": 0.0007355830166488886,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-mini-case0]",
"lineno": 332,
"outcome": "passed",
"keywords": [
"test_chat_streaming_tool_choice_none[gpt-4o-mini-case0]",
"parametrize",
"pytestmark",
"gpt-4o-mini-case0",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "case0"
},
"setup": {
"duration": 0.009106541983783245,
"outcome": "passed"
},
"call": {
"duration": 0.6319579591508955,
"outcome": "passed"
},
"teardown": {
"duration": 0.0001566251739859581,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-text_then_weather_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-text_then_weather_tool]",
"parametrize",
"pytestmark",
"gpt-4o-text_then_weather_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "text_then_weather_tool"
},
"setup": {
"duration": 0.007579708006232977,
"outcome": "passed"
},
"call": {
"duration": 2.0561707499437034,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002633749973028898,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-weather_tool_then_text]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-weather_tool_then_text]",
"parametrize",
"pytestmark",
"gpt-4o-weather_tool_then_text",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "weather_tool_then_text"
},
"setup": {
"duration": 0.00797787494957447,
"outcome": "passed"
},
"call": {
"duration": 1.275011499878019,
"outcome": "passed"
},
"teardown": {
"duration": 0.0004980000667273998,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"parametrize",
"pytestmark",
"gpt-4o-add_product_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "add_product_tool"
},
"setup": {
"duration": 0.009830792201682925,
"outcome": "passed"
},
"call": {
"duration": 1.7245257501490414,
"outcome": "passed"
},
"teardown": {
"duration": 0.0008070000912994146,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-get_then_create_event_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-get_then_create_event_tool]",
"parametrize",
"pytestmark",
"gpt-4o-get_then_create_event_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "get_then_create_event_tool"
},
"setup": {
"duration": 0.007216874975711107,
"outcome": "passed"
},
"call": {
"duration": 3.557671125046909,
"outcome": "passed"
},
"teardown": {
"duration": 0.00018779095262289047,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-compare_monthly_expense_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-compare_monthly_expense_tool]",
"parametrize",
"pytestmark",
"gpt-4o-compare_monthly_expense_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "compare_monthly_expense_tool"
},
"setup": {
"duration": 0.01774512487463653,
"outcome": "passed"
},
"call": {
"duration": 3.471029832959175,
"outcome": "passed"
},
"teardown": {
"duration": 0.0006218329071998596,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-text_then_weather_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-text_then_weather_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-text_then_weather_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "text_then_weather_tool"
},
"setup": {
"duration": 0.0074716671369969845,
"outcome": "passed"
},
"call": {
"duration": 1.4332320829853415,
"outcome": "passed"
},
"teardown": {
"duration": 0.00024041696451604366,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-weather_tool_then_text]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-weather_tool_then_text]",
"parametrize",
"pytestmark",
"gpt-4o-mini-weather_tool_then_text",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "weather_tool_then_text"
},
"setup": {
"duration": 0.012363416142761707,
"outcome": "passed"
},
"call": {
"duration": 1.0449200000148267,
"outcome": "passed"
},
"teardown": {
"duration": 0.00017075007781386375,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-add_product_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-add_product_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-add_product_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "add_product_tool"
},
"setup": {
"duration": 0.007610665867105126,
"outcome": "passed"
},
"call": {
"duration": 1.1585895828902721,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015249988064169884,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-get_then_create_event_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-get_then_create_event_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-get_then_create_event_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "get_then_create_event_tool"
},
"setup": {
"duration": 0.015131499851122499,
"outcome": "passed"
},
"call": {
"duration": 3.4365211671683937,
"outcome": "passed"
},
"teardown": {
"duration": 0.00016770907677710056,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-compare_monthly_expense_tool]",
"lineno": 360,
"outcome": "passed",
"keywords": [
"test_chat_non_streaming_multi_turn_tool_calling[gpt-4o-mini-compare_monthly_expense_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-compare_monthly_expense_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "compare_monthly_expense_tool"
},
"setup": {
"duration": 0.011571999872103333,
"outcome": "passed"
},
"call": {
"duration": 2.5175172919407487,
"outcome": "passed"
},
"teardown": {
"duration": 0.0006474158726632595,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-text_then_weather_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-text_then_weather_tool]",
"parametrize",
"pytestmark",
"gpt-4o-text_then_weather_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "text_then_weather_tool"
},
"setup": {
"duration": 0.008532207924872637,
"outcome": "passed"
},
"call": {
"duration": 4.933332832995802,
"outcome": "passed"
},
"teardown": {
"duration": 0.00029174983501434326,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-weather_tool_then_text]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-weather_tool_then_text]",
"parametrize",
"pytestmark",
"gpt-4o-weather_tool_then_text",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "weather_tool_then_text"
},
"setup": {
"duration": 0.006954000098630786,
"outcome": "passed"
},
"call": {
"duration": 3.7280790000222623,
"outcome": "passed"
},
"teardown": {
"duration": 0.0022806660272181034,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"parametrize",
"pytestmark",
"gpt-4o-add_product_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "add_product_tool"
},
"setup": {
"duration": 0.0073084591422230005,
"outcome": "passed"
},
"call": {
"duration": 2.8530333330854774,
"outcome": "passed"
},
"teardown": {
"duration": 0.0005582920275628567,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-get_then_create_event_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-get_then_create_event_tool]",
"parametrize",
"pytestmark",
"gpt-4o-get_then_create_event_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "get_then_create_event_tool"
},
"setup": {
"duration": 0.008092042058706284,
"outcome": "passed"
},
"call": {
"duration": 2.3742935829795897,
"outcome": "passed"
},
"teardown": {
"duration": 0.0005646671634167433,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-compare_monthly_expense_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-compare_monthly_expense_tool]",
"parametrize",
"pytestmark",
"gpt-4o-compare_monthly_expense_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "compare_monthly_expense_tool"
},
"setup": {
"duration": 0.010496499948203564,
"outcome": "passed"
},
"call": {
"duration": 3.235504541080445,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015583401545882225,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-text_then_weather_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-text_then_weather_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-text_then_weather_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "text_then_weather_tool"
},
"setup": {
"duration": 0.01372083299793303,
"outcome": "passed"
},
"call": {
"duration": 1.3791909590363503,
"outcome": "passed"
},
"teardown": {
"duration": 0.00015145796351134777,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-weather_tool_then_text]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-weather_tool_then_text]",
"parametrize",
"pytestmark",
"gpt-4o-mini-weather_tool_then_text",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "weather_tool_then_text"
},
"setup": {
"duration": 0.006975916214287281,
"outcome": "passed"
},
"call": {
"duration": 0.8690883328672498,
"outcome": "passed"
},
"teardown": {
"duration": 0.0005298329051584005,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-add_product_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-add_product_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-add_product_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "add_product_tool"
},
"setup": {
"duration": 0.008625000016763806,
"outcome": "passed"
},
"call": {
"duration": 1.6651969160884619,
"outcome": "passed"
},
"teardown": {
"duration": 0.0004458329640328884,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-get_then_create_event_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-get_then_create_event_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-get_then_create_event_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "get_then_create_event_tool"
},
"setup": {
"duration": 0.009998749941587448,
"outcome": "passed"
},
"call": {
"duration": 3.24621754209511,
"outcome": "passed"
},
"teardown": {
"duration": 0.00047412491403520107,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-compare_monthly_expense_tool]",
"lineno": 451,
"outcome": "passed",
"keywords": [
"test_chat_streaming_multi_turn_tool_calling[gpt-4o-mini-compare_monthly_expense_tool]",
"parametrize",
"pytestmark",
"gpt-4o-mini-compare_monthly_expense_tool",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "compare_monthly_expense_tool"
},
"setup": {
"duration": 0.007803959073498845,
"outcome": "passed"
},
"call": {
"duration": 4.1487593341153115,
"outcome": "passed"
},
"teardown": {
"duration": 0.0007139160297811031,
"outcome": "passed"
}
}
],
"run_timestamp": 1744841358
}
Reference in a new issue View git blame Copy permalink