mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
79bed44b04
Propagate test IDs from client to server via HTTP headers to maintain proper test isolation when running with server-based stack configs. Without this, recorded/replayed inference requests in server mode would leak across tests. Changes: - Patch client _prepare_request to inject test ID into provider data header - Sync test context from provider data on server side before storage operations - Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config - Configure console width for cleaner log output in CI - Add SQLITE_STORE_DIR temp directory for test data isolation
90 lines
2.7 KiB
JSON
90 lines
2.7 KiB
JSON
{
|
|
"test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_structured_output[txt=ollama/llama3.2:3b-instruct-fp16-inference:chat_completion:structured_output]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful assistant. Michael Jordan was born in 1963. He played basketball for the Chicago Bulls for 15 seasons."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Please give me information about Michael Jordan."
|
|
}
|
|
],
|
|
"response_format": {
|
|
"type": "json_schema",
|
|
"json_schema": {
|
|
"name": "AnswerFormat",
|
|
"schema": {
|
|
"properties": {
|
|
"first_name": {
|
|
"title": "First Name",
|
|
"type": "string"
|
|
},
|
|
"last_name": {
|
|
"title": "Last Name",
|
|
"type": "string"
|
|
},
|
|
"year_of_birth": {
|
|
"title": "Year Of Birth",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"first_name",
|
|
"last_name",
|
|
"year_of_birth"
|
|
],
|
|
"title": "AnswerFormat",
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-fec22760875c",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "{\"first_name\": \"Michael\", \"last_name\": \"Jordan\", \"year_of_birth\": 1963}\n\n \t\t\t\t\t \t\t\t\t\t \t\t",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 32,
|
|
"prompt_tokens": 60,
|
|
"total_tokens": 92,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|