mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 22:33:48 +00:00
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
59 lines
1.5 KiB
JSON
59 lines
1.5 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.together.xyz/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Hello"
|
|
}
|
|
],
|
|
"max_tokens": 10
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-f4c5ae637cd1",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "Hello. How can I assist you today?",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": []
|
|
},
|
|
"seed": 6760981245874068000
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 10,
|
|
"prompt_tokens": 36,
|
|
"total_tokens": 46,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null,
|
|
"cached_tokens": 0
|
|
},
|
|
"prompt": []
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|