llama-stack-mirror/tests/integration/test_cases/openai/responses.json
Derek Higgins 8951765584 test: improve test reliability and model compatibility
- Update earth question to be more specific with multiple choice format
  to prevent Llama-3.2-1B-Instruct from rambling about other planets
- Skip test_text_chat_completion_structured_output as it sometimes
  times out during CI execution again with Llama-3.2-1B-Instruct on vllm

Signed-off-by: Derek Higgins <derekh@redhat.com>
2025-09-24 09:38:42 +01:00

37 lines
803 B
JSON

{
"non_streaming_01": {
"data": {
"question": "Humans live on which planet: Mars, Venus, or Earth?",
"expected": "Earth"
}
},
"non_streaming_02": {
"data": {
"question": "Which planet has rings around it with a name starting with letter S?",
"expected": "Saturn"
}
},
"streaming_01": {
"data": {
"question": "What's the name of the Sun in latin?",
"expected": "Sol"
}
},
"streaming_02": {
"data": {
"question": "What is the name of the US captial?",
"expected": "Washington"
}
},
"tools_web_search_01": {
"data": {
"input": "How many experts does the Llama 4 Maverick model have?",
"tools": [
{
"type": "web_search"
}
],
"expected": "128"
}
}
}