mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
3f36bfaeaa
IDs are now deterministic hashes based on request content, and timestamps are normalized to constants, eliminating spurious changes when re-recording tests. ## Changes - Updated `inference_recorder.py` to normalize IDs and timestamps during recording - Added `scripts/normalize_recordings.py` utility to re-normalize existing recordings - Created documentation in `tests/integration/recordings/README.md` - Normalized 350 existing recording files
56 lines
1.8 KiB
JSON
56 lines
1.8 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8080/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Hello, world!"
|
|
}
|
|
],
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-27463384d1a3",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "<think>\nOkay, the user just said \"Hello, world!\" so I need to respond in a friendly way. My prompt says to respond in the same style, so I should start with \"Hello, world!\" but maybe add some helpful information. Let me think. Since the user is probably testing or just sharing, a simple \"Hello, world!\" with a question would be best for user interaction. I'll make sure to keep it positive and open-ended.\n</think>\n\nHello, world! \ud83d\ude0a What do you need today?",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "3.3.5-dev0-sha-1b90c50",
|
|
"usage": {
|
|
"completion_tokens": 108,
|
|
"prompt_tokens": 12,
|
|
"total_tokens": 120,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|