llama-stack-mirror/tests/integration/eval/recordings/b52a054b314c8b42634c4a9ef76280591f73cf26c00b7308dde7d19a1ced016c.json
Ashwin Bharambe 045a0c1d57
feat(tests): implement test isolation for inference recordings (#3681)
Uses test_id in request hashes and test-scoped subdirectories to prevent
cross-test contamination. Model list endpoints exclude test_id to enable
merging recordings from different servers.

Additionally, this PR adds a `record-if-missing` mode (which we will use
instead of `record` which records everything) which is very useful.

🤖 Co-authored with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-10-04 11:34:18 -07:00

56 lines
1.4 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": "What is the capital of France?"
}
],
"max_tokens": 0
},
"endpoint": "/v1/chat/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "rec-e25ab43491af",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "The capital of France is Paris.",
"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": 8,
"prompt_tokens": 32,
"total_tokens": 40,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}