llama-stack-mirror/tests/integration/eval/recordings/b52a054b314c8b42634c4a9ef76280591f73cf26c00b7308dde7d19a1ced016c.json
Ashwin Bharambe 79bed44b04
fix(tests): ensure test isolation in server mode (#3737)
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
2025-10-08 12:03:36 -07:00

57 lines
1.5 KiB
JSON

{
"test_id": "tests/integration/eval/test_eval.py::test_evaluate_rows[txt=ollama/llama3.2:3b-instruct-fp16-basic::equality]",
"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-b52a054b314c",
"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
}
}