mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
c62a09ab76
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>
92 lines
3.4 KiB
JSON
Generated
92 lines
3.4 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/inference/test_tools_with_schemas.py::TestOpenAICompatibility::test_openai_format_preserves_complex_schemas[openai_client-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": "Process this data"
|
|
}
|
|
],
|
|
"max_tokens": 4096,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "process_data",
|
|
"description": "Process structured data",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"data": {
|
|
"$ref": "#/$defs/DataObject"
|
|
}
|
|
},
|
|
"$defs": {
|
|
"DataObject": {
|
|
"type": "object",
|
|
"properties": {
|
|
"values": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "number"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-524ead18daad",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "<think>\nOkay, the user wants me to process the data. Let me check the available tools. There's a function called process_data that takes an object with a 'data' parameter. The data is an array of numbers. But the user hasn't provided any specific data yet. They just said \"Process this data.\" Hmm, maybe they expect me to prompt them for the data first. Wait, maybe there's a misunderstanding. Did they include the data in the conversation history? Let me look back. The user's message is \"Process this data.\" No data provided. Oh, maybe they made a mistake and forgot to include it. I need to ask them to provide the data so I can proceed. Let me confirm if there's any data mentioned. No, the current input is just the instruction. So I should ask the user to supply the data array of numbers to process.\n</think>\n\nPlease provide the structured data you'd like me to process. For example, an array of numbers like `[1, 2, 3]`.",
|
|
"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": 212,
|
|
"prompt_tokens": 180,
|
|
"total_tokens": 392,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"prompt_logprobs": null,
|
|
"kv_transfer_params": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|