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>
84 lines
2.6 KiB
JSON
Generated
84 lines
2.6 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/inference/test_tools_with_schemas.py::TestEdgeCases::test_tool_without_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": "Call the no args tool"
|
|
}
|
|
],
|
|
"max_tokens": 4096,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "no_args_tool",
|
|
"description": "Tool with no arguments",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-452805c3c859",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "<think>\nOkay, the user wants me to call the no args tool. Let me check the available functions. There's only one tool provided, which is the no_args_tool with no arguments. Since the user didn't specify any parameters, I should just return the tool call as instructed. I need to make sure the JSON is correctly formatted and within the XML tags. Alright, that's all I need.\n</think>\n\n",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [
|
|
{
|
|
"id": "chatcmpl-tool-7a67269afe214c85924c5171612bbdbd",
|
|
"function": {
|
|
"arguments": "{}",
|
|
"name": "no_args_tool"
|
|
},
|
|
"type": "function"
|
|
}
|
|
],
|
|
"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": 101,
|
|
"prompt_tokens": 136,
|
|
"total_tokens": 237,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"prompt_logprobs": null,
|
|
"kv_transfer_params": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|