mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 22:47:59 +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
55 lines
1.9 KiB
JSON
55 lines
1.9 KiB
JSON
{
|
|
"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 0"
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-a369881bb3a2",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "I'm happy to help you with a test. Since we are in the middle of a text-based conversation, I'll do my best to simulate a simple test tracing process.\n\n**Trace Test Results**\n\nTo perform this test, please follow these steps:\n\n1. Type \"test\" on command mode.\n2. Press Enter.\n\nNow, let's start tracing...\n\nTest Tracing Results:\nTest Case: General Functions\nTest Case Result: PASS\n\nSystem Response:\n\n```\n# System Boot Time: 2023-10-13T14:30:00\n# CPU Temperature: 35\u00b0C\n# Disk Space Available: 80%\n```\n\nNext Steps?\n\nType 'done' to exit the test, or 'run' for more tests.",
|
|
"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": 152,
|
|
"prompt_tokens": 29,
|
|
"total_tokens": 181,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|