mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Integration Tests (Replay) / generate-matrix (push) Successful in 4s
Python Package Build Test / build (3.13) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Pre-commit / pre-commit (push) Failing after 6s
Test External API and Providers / test-external (venv) (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 14s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 5s
Python Package Build Test / build (3.12) (push) Failing after 22s
UI Tests / ui-tests (22) (push) Successful in 57s
o Introduces vLLM provider support to the record/replay testing framework o Enabling both recording and replay of vLLM API interactions alongside existing Ollama support. The changes enable testing of vLLM functionality. vLLM tests focus on inference capabilities, while Ollama continues to exercise the full API surface including vision features. -- This is an alternative to #3128 , using qwen3 instead of llama 3.2 1B appears to be more capable at structure output and tool calls. --------- Signed-off-by: Derek Higgins <derekh@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
114 lines
4.5 KiB
JSON
Generated
114 lines
4.5 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/inference/test_tools_with_schemas.py::TestChatCompletionWithTools::test_tool_with_complex_schema[txt=vllm/Qwen/Qwen3-0.6B]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Book a flight from SFO to JFK for John Doe"
|
|
}
|
|
],
|
|
"max_tokens": 4096,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "book_flight",
|
|
"description": "Book a flight",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"flight": {
|
|
"$ref": "#/$defs/FlightInfo"
|
|
},
|
|
"passenger": {
|
|
"$ref": "#/$defs/Passenger"
|
|
}
|
|
},
|
|
"required": [
|
|
"flight",
|
|
"passenger"
|
|
],
|
|
"$defs": {
|
|
"FlightInfo": {
|
|
"type": "object",
|
|
"properties": {
|
|
"from": {
|
|
"type": "string"
|
|
},
|
|
"to": {
|
|
"type": "string"
|
|
},
|
|
"date": {
|
|
"type": "string",
|
|
"format": "date"
|
|
}
|
|
}
|
|
},
|
|
"Passenger": {
|
|
"type": "object",
|
|
"properties": {
|
|
"name": {
|
|
"type": "string"
|
|
},
|
|
"age": {
|
|
"type": "integer"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-cfb292c0f41d",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "<think>\nOkay, the user wants to book a flight from SFO to JFK for John Doe. Let me check the tools available. The provided function is book_flight, which requires flight information and a passenger. The parameters needed are flight (as a FlightInfo object) and passenger (with name and age). The user mentioned SFO to JFK, so the flight details are from and to. The passenger's name is John Doe, but the age isn't provided. Wait, the function parameters require the passenger's name and age, but the user only mentioned the name. Maybe the age is missing? But the user didn't specify it, so perhaps I should note that the age is required. However, the function's required parameters are flight and passenger, so even if age is missing, the function can't be called without it. So I need to include both flight info and passenger details. The user's message only gives the name and destination, not the flight details or age. Therefore, I need to ask for the flight details and the passenger's age. But the user hasn't provided those. So I can't proceed with the function call. Wait, but maybe the user expects me to assume some default? No, the function requires all parameters. Since the user hasn't provided flight details or age, I can't call the function. So the correct response is to prompt the user for those details.\n</think>\n\nThe booking requires the flight details and passenger's age. Could you provide the flight number and John Doe's age?",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [],
|
|
"reasoning_content": null
|
|
},
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 310,
|
|
"prompt_tokens": 261,
|
|
"total_tokens": 571,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"prompt_logprobs": null,
|
|
"kv_transfer_params": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|