mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-15 23:31:29 +00:00
93300019bd
These seven test files were on _RESPX_CONFLICTING_FILES, which made the
auto-marker skip them entirely. Inspecting the source shows the only
respx artifact is a top-level 'from respx import MockRouter' that no
test ever uses - no @pytest.mark.respx, no respx_mock fixture, no
respx.mock context manager. The import is dead code left over from a
previous mocking pattern.
Now that apply_vcr_auto_marker_to_items detects respx per-item via the
marker / fixture chain (b637d9f64a), the file-level skip is no longer
needed for these files - they were the reason the OpenAI tests
(test_o3_reasoning_effort, test_streaming_response[o1/o3-mini],
TestOpenAIO1::test_streaming, TestOpenAIChatCompletion::test_web_search,
TestOpenAIO3::test_web_search, etc.) ran live every CI build despite
the cassette cache being healthy.
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
33 lines
908 B
Python
33 lines
908 B
Python
import json
|
|
import os
|
|
import sys
|
|
from datetime import datetime
|
|
from unittest.mock import AsyncMock
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
import litellm
|
|
from litellm import Choices, Message, ModelResponse
|
|
from litellm.types.utils import PromptTokensDetails
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_prompt_caching():
|
|
"""
|
|
Tests that:
|
|
- prompt_tokens_details is correctly handled and returned as PromptTokensDetails type
|
|
"""
|
|
response1 = await litellm.acompletion(
|
|
model="gpt-4o-mini",
|
|
messages=[{"role": "user", "content": "hi"}],
|
|
)
|
|
print("response1", response1)
|
|
print("response1.usage", response1.usage)
|
|
print("type of prompt_tokens_details", type(response1.usage.prompt_tokens_details))
|
|
assert isinstance(response1.usage.prompt_tokens_details, PromptTokensDetails)
|