mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 22:33:48 +00:00
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
57 lines
2.1 KiB
JSON
57 lines
2.1 KiB
JSON
{
|
|
"test_id": null,
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Test trace openai 2"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-395c30078677",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'd be happy to help you test the new text-based interface for the OpenAI chat model, known as \"ChatGPT\". Here's how we can do it:\n\n**What is the new interface?**\n\nThe new interface is a simple text-based interface that allows you to interact with an AI model using plain text commands. You can type in a question or prompt, and the AI will respond with a relevant answer.\n\n**How to test the interface:**\n\n1. Type your query in the chat window below.\n2. Press enter to submit your query.\n3. The AI will respond with an answer, which you can then examine and ask follow-up questions about.\n\nGo ahead and try something! What would you like to know or discuss?",
|
|
"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": 151,
|
|
"prompt_tokens": 31,
|
|
"total_tokens": 182,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|