llama-stack-mirror/tests/verifications/test_results/openai.json
Eric Huang d5abe2ec2e tests: add multi_image test
# What does this PR do?


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

2161 lines
61 KiB
JSON

{
"created": 1744915847.9751267,
"duration": 148.2403597831726,
"exitcode": 0,
"root": "/home/erichuang/llama-stack",
"environment": {},
"summary": {
"passed": 56,
"total": 56,
"collected": 56
},
"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": 95
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-saturn]",
"type": "Function",
"lineno": 95
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-earth]",
"type": "Function",
"lineno": 95
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
"type": "Function",
"lineno": 95
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-earth]",
"type": "Function",
"lineno": 114
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-saturn]",
"type": "Function",
"lineno": 114
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-earth]",
"type": "Function",
"lineno": 114
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-saturn]",
"type": "Function",
"lineno": 114
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-case0]",
"type": "Function",
"lineno": 138
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 138
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-case0]",
"type": "Function",
"lineno": 157
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 157
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-calendar]",
"type": "Function",
"lineno": 181
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-math]",
"type": "Function",
"lineno": 181
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
"type": "Function",
"lineno": 181
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
"type": "Function",
"lineno": 181
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-calendar]",
"type": "Function",
"lineno": 204
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-math]",
"type": "Function",
"lineno": 204
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
"type": "Function",
"lineno": 204
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-math]",
"type": "Function",
"lineno": 204
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-case0]",
"type": "Function",
"lineno": 226
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 226
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-case0]",
"type": "Function",
"lineno": 250
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 250
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-case0]",
"type": "Function",
"lineno": 278
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 278
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-case0]",
"type": "Function",
"lineno": 302
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 302
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-case0]",
"type": "Function",
"lineno": 329
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 329
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-case0]",
"type": "Function",
"lineno": 352
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-mini-case0]",
"type": "Function",
"lineno": 352
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 380
},
{
"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": 471
},
{
"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": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"type": "Function",
"lineno": 471
},
{
"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": 471
},
{
"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": 471
},
{
"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": 471
},
{
"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": 471
},
{
"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": 471
},
{
"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": 471
},
{
"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": 471
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-stream=False]",
"type": "Function",
"lineno": 554
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-stream=True]",
"type": "Function",
"lineno": 554
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-mini-stream=False]",
"type": "Function",
"lineno": 554
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-mini-stream=True]",
"type": "Function",
"lineno": 554
}
]
}
],
"tests": [
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-earth]",
"lineno": 95,
"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": 0.10051544290035963,
"outcome": "passed"
},
"call": {
"duration": 0.9317309083417058,
"outcome": "passed"
},
"teardown": {
"duration": 0.00028314627707004547,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-saturn]",
"lineno": 95,
"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": 0.072531433776021,
"outcome": "passed"
},
"call": {
"duration": 0.8465302847325802,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002783900126814842,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-earth]",
"lineno": 95,
"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": 0.07362798601388931,
"outcome": "passed"
},
"call": {
"duration": 0.4735605753958225,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002751639112830162,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
"lineno": 95,
"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": 0.07427007798105478,
"outcome": "passed"
},
"call": {
"duration": 0.9180357335135341,
"outcome": "passed"
},
"teardown": {
"duration": 0.000255512073636055,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-earth]",
"lineno": 114,
"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": 0.07261236105114222,
"outcome": "passed"
},
"call": {
"duration": 0.887298776768148,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002456493675708771,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-saturn]",
"lineno": 114,
"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": 0.072073626331985,
"outcome": "passed"
},
"call": {
"duration": 0.9108476722612977,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003651324659585953,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-earth]",
"lineno": 114,
"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": 0.0768214799463749,
"outcome": "passed"
},
"call": {
"duration": 0.5603971695527434,
"outcome": "passed"
},
"teardown": {
"duration": 0.00028181448578834534,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-saturn]",
"lineno": 114,
"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": 0.1015146067366004,
"outcome": "passed"
},
"call": {
"duration": 1.0284570446237922,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026540644466876984,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-case0]",
"lineno": 138,
"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": 0.07235357817262411,
"outcome": "passed"
},
"call": {
"duration": 2.9321771170943975,
"outcome": "passed"
},
"teardown": {
"duration": 0.00023869052529335022,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-mini-case0]",
"lineno": 138,
"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": 0.08063248638063669,
"outcome": "passed"
},
"call": {
"duration": 3.1335192881524563,
"outcome": "passed"
},
"teardown": {
"duration": 0.00023141037672758102,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-case0]",
"lineno": 157,
"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": 0.07109073270112276,
"outcome": "passed"
},
"call": {
"duration": 4.281152673996985,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002774428576231003,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-mini-case0]",
"lineno": 157,
"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": 0.07122835051268339,
"outcome": "passed"
},
"call": {
"duration": 3.1493511451408267,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025907624512910843,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-calendar]",
"lineno": 181,
"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": 0.07077997270971537,
"outcome": "passed"
},
"call": {
"duration": 1.0191298499703407,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002577090635895729,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-math]",
"lineno": 181,
"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": 0.0717731025069952,
"outcome": "passed"
},
"call": {
"duration": 4.3670165073126554,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002760225906968117,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
"lineno": 181,
"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": 0.07413097750395536,
"outcome": "passed"
},
"call": {
"duration": 0.7250115219503641,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027088727802038193,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
"lineno": 181,
"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": 0.07421348057687283,
"outcome": "passed"
},
"call": {
"duration": 4.159640856087208,
"outcome": "passed"
},
"teardown": {
"duration": 0.000304369255900383,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-calendar]",
"lineno": 204,
"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": 0.07243203837424517,
"outcome": "passed"
},
"call": {
"duration": 0.8918390739709139,
"outcome": "passed"
},
"teardown": {
"duration": 0.00045058969408273697,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-math]",
"lineno": 204,
"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": 0.07240029145032167,
"outcome": "passed"
},
"call": {
"duration": 5.932509887032211,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002680215984582901,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
"lineno": 204,
"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": 0.0948595218360424,
"outcome": "passed"
},
"call": {
"duration": 0.7575554186478257,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002606986090540886,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-math]",
"lineno": 204,
"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": 0.07143882941454649,
"outcome": "passed"
},
"call": {
"duration": 3.072851055301726,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002756454050540924,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-case0]",
"lineno": 226,
"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": 0.07490892708301544,
"outcome": "passed"
},
"call": {
"duration": 0.7080789571627975,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026887841522693634,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
"lineno": 226,
"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": 0.07331829704344273,
"outcome": "passed"
},
"call": {
"duration": 0.5377899333834648,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002817092463374138,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-case0]",
"lineno": 250,
"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": 0.07127166073769331,
"outcome": "passed"
},
"call": {
"duration": 5.521908577531576,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026642531156539917,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
"lineno": 250,
"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": 0.07290575932711363,
"outcome": "passed"
},
"call": {
"duration": 2.046463970094919,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002727797254920006,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-case0]",
"lineno": 278,
"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": 0.10423497296869755,
"outcome": "passed"
},
"call": {
"duration": 1.004861214198172,
"outcome": "passed"
},
"teardown": {
"duration": 0.00024383515119552612,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_required[gpt-4o-mini-case0]",
"lineno": 278,
"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": 0.07122009992599487,
"outcome": "passed"
},
"call": {
"duration": 0.7581121334806085,
"outcome": "passed"
},
"teardown": {
"duration": 0.00040143169462680817,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-case0]",
"lineno": 302,
"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": 0.08253305684775114,
"outcome": "passed"
},
"call": {
"duration": 1.557566043920815,
"outcome": "passed"
},
"teardown": {
"duration": 0.000243467278778553,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_required[gpt-4o-mini-case0]",
"lineno": 302,
"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": 0.07361925579607487,
"outcome": "passed"
},
"call": {
"duration": 0.8178399363532662,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002515781670808792,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-case0]",
"lineno": 329,
"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": 0.07521046791225672,
"outcome": "passed"
},
"call": {
"duration": 0.6787212993949652,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002325829118490219,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_choice_none[gpt-4o-mini-case0]",
"lineno": 329,
"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": 0.07222333271056414,
"outcome": "passed"
},
"call": {
"duration": 0.9725492037832737,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002515064552426338,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-case0]",
"lineno": 352,
"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": 0.07048032432794571,
"outcome": "passed"
},
"call": {
"duration": 0.7804577611386776,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027917418628931046,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_choice_none[gpt-4o-mini-case0]",
"lineno": 352,
"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": 0.06972779426723719,
"outcome": "passed"
},
"call": {
"duration": 0.5892468513920903,
"outcome": "passed"
},
"teardown": {
"duration": 0.00024467986077070236,
"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": 380,
"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": 0.07078671548515558,
"outcome": "passed"
},
"call": {
"duration": 2.0133057748898864,
"outcome": "passed"
},
"teardown": {
"duration": 0.000314236618578434,
"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": 380,
"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": 0.07210633344948292,
"outcome": "passed"
},
"call": {
"duration": 1.4769609719514847,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026525091379880905,
"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": 380,
"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": 0.11760899517685175,
"outcome": "passed"
},
"call": {
"duration": 2.2442161748185754,
"outcome": "passed"
},
"teardown": {
"duration": 0.00022951047867536545,
"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": 380,
"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": 0.0710864681750536,
"outcome": "passed"
},
"call": {
"duration": 4.662528890185058,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002990514039993286,
"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": 380,
"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": 0.07443534769117832,
"outcome": "passed"
},
"call": {
"duration": 2.6949840802699327,
"outcome": "passed"
},
"teardown": {
"duration": 0.00024112220853567123,
"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": 380,
"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": 0.06947629060596228,
"outcome": "passed"
},
"call": {
"duration": 1.6329273879528046,
"outcome": "passed"
},
"teardown": {
"duration": 0.00028422847390174866,
"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": 380,
"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": 0.07201728876680136,
"outcome": "passed"
},
"call": {
"duration": 1.3507471680641174,
"outcome": "passed"
},
"teardown": {
"duration": 0.00026798248291015625,
"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": 380,
"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": 0.07063739560544491,
"outcome": "passed"
},
"call": {
"duration": 1.935924295336008,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027618370950222015,
"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": 380,
"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": 0.07451055385172367,
"outcome": "passed"
},
"call": {
"duration": 5.712521097622812,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002723056823015213,
"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": 380,
"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": 0.07001785095781088,
"outcome": "passed"
},
"call": {
"duration": 2.303163451142609,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002651633694767952,
"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": 471,
"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": 0.08379010856151581,
"outcome": "passed"
},
"call": {
"duration": 2.773816448636353,
"outcome": "passed"
},
"teardown": {
"duration": 0.00029759760946035385,
"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": 471,
"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": 0.08924641087651253,
"outcome": "passed"
},
"call": {
"duration": 1.3787386734038591,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025635119527578354,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_multi_turn_tool_calling[gpt-4o-add_product_tool]",
"lineno": 471,
"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": 0.07048780098557472,
"outcome": "passed"
},
"call": {
"duration": 5.141806213185191,
"outcome": "passed"
},
"teardown": {
"duration": 0.00024782493710517883,
"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": 471,
"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": 0.07248174957931042,
"outcome": "passed"
},
"call": {
"duration": 4.618824512697756,
"outcome": "passed"
},
"teardown": {
"duration": 0.000261564739048481,
"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": 471,
"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": 0.07576782070100307,
"outcome": "passed"
},
"call": {
"duration": 7.610115051269531,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025057513266801834,
"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": 471,
"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": 0.07933000661432743,
"outcome": "passed"
},
"call": {
"duration": 1.6595397107303143,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027087051421403885,
"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": 471,
"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": 0.07243796810507774,
"outcome": "passed"
},
"call": {
"duration": 1.5991155235096812,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002850182354450226,
"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": 471,
"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": 0.07210367918014526,
"outcome": "passed"
},
"call": {
"duration": 1.5363366417586803,
"outcome": "passed"
},
"teardown": {
"duration": 0.0002558305859565735,
"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": 471,
"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": 0.08108823746442795,
"outcome": "passed"
},
"call": {
"duration": 3.4596447916701436,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025700684636831284,
"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": 471,
"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": 0.08756247535347939,
"outcome": "passed"
},
"call": {
"duration": 2.7237467989325523,
"outcome": "passed"
},
"teardown": {
"duration": 0.0003129318356513977,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-stream=False]",
"lineno": 554,
"outcome": "passed",
"keywords": [
"test_chat_multi_turn_multiple_images[gpt-4o-stream=False]",
"parametrize",
"pytestmark",
"gpt-4o-stream=False",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "stream=False"
},
"setup": {
"duration": 0.07461991906166077,
"outcome": "passed"
},
"call": {
"duration": 7.691402747295797,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027259159833192825,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-stream=True]",
"lineno": 554,
"outcome": "passed",
"keywords": [
"test_chat_multi_turn_multiple_images[gpt-4o-stream=True]",
"parametrize",
"pytestmark",
"gpt-4o-stream=True",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o",
"case_id": "stream=True"
},
"setup": {
"duration": 0.08226520381867886,
"outcome": "passed"
},
"call": {
"duration": 8.066991656087339,
"outcome": "passed"
},
"teardown": {
"duration": 0.00027418695390224457,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-mini-stream=False]",
"lineno": 554,
"outcome": "passed",
"keywords": [
"test_chat_multi_turn_multiple_images[gpt-4o-mini-stream=False]",
"parametrize",
"pytestmark",
"gpt-4o-mini-stream=False",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "stream=False"
},
"setup": {
"duration": 0.07172532472759485,
"outcome": "passed"
},
"call": {
"duration": 6.693852873519063,
"outcome": "passed"
},
"teardown": {
"duration": 0.00025922991335392,
"outcome": "passed"
}
},
{
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_multi_turn_multiple_images[gpt-4o-mini-stream=True]",
"lineno": 554,
"outcome": "passed",
"keywords": [
"test_chat_multi_turn_multiple_images[gpt-4o-mini-stream=True]",
"parametrize",
"pytestmark",
"gpt-4o-mini-stream=True",
"test_chat_completion.py",
"openai_api",
"verifications",
"tests",
"llama-stack",
""
],
"metadata": {
"model": "gpt-4o-mini",
"case_id": "stream=True"
},
"setup": {
"duration": 0.07190134841948748,
"outcome": "passed"
},
"call": {
"duration": 5.758517139591277,
"outcome": "passed"
},
"teardown": {
"duration": 0.0016343863680958748,
"outcome": "passed"
}
}
],
"run_timestamp": 1744915699
}