mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-12 03:48:56 +00:00
f6bb87739d
* test(integration): move the openai cost tracking cases from cost_tracking_cases.json to CostTrackingTestCase literals Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(integration): move the remaining cost tracking cases, the cost map and the batch/realtime cases from cost_tracking_cases.json to Python literals (#45885) Co-authored-by: kerry <kerry@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: kerry <kerry@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
42 lines
1.9 KiB
Python
42 lines
1.9 KiB
Python
"""A streamed request bills exactly what the same request bills without streaming.
|
|
|
|
Streaming reconstructs the response, its usage and its model name from chunks after the fact, in a separate code
|
|
path from the non-streamed one (LIT-6241, LIT-6872, LIT-7632, LIT-7729, LIT-9044, LIT-9065). Each case is a plain and
|
|
a streamed CostTrackingTestCase for one request, sent through the same key, and both LiteLLM_SpendLogs rows must
|
|
bill the case's expected row.
|
|
|
|
Three cells are the native routes (chat, /v1/messages, /v1/responses); the rest are the bridges that translate one
|
|
API into another before the provider call, each with its own stream reassembly. PARITY_CASES are the plain and
|
|
streamed twins migrated from cost_tracking_cases.json that bill the same row.
|
|
"""
|
|
|
|
from typing import Final
|
|
|
|
import pytest
|
|
from integration._support.client import Gateway
|
|
from integration.cost_calculation.catalog import PARITY_CASES
|
|
from integration.cost_calculation.stream_parity.bases import anthropic, bedrock, openai, openai_responses, xai
|
|
from integration.cost_calculation.stream_parity.case import StreamParityTestCase
|
|
from integration.cost_calculation.stream_parity.runner import assert_stream_parity
|
|
|
|
NATIVE: Final = (
|
|
openai.GPT_6_1_SOL_CHAT_COMPLETIONS_PARITY,
|
|
anthropic.CLAUDE_OPUS_5_5_MESSAGES_PARITY,
|
|
openai_responses.GPT_6_1_SOL_RESPONSES_PARITY,
|
|
)
|
|
BRIDGES: Final = (
|
|
xai.GROK_4_7_MESSAGES_PARITY,
|
|
openai.GPT_6_1_SOL_MESSAGES_PARITY,
|
|
bedrock.CLAUDE_OPUS_5_5_CONVERSE_MESSAGES_PARITY,
|
|
openai_responses.GPT_5_5_PRO_CHAT_COMPLETIONS_PARITY,
|
|
anthropic.CLAUDE_OPUS_5_5_RESPONSES_PARITY,
|
|
)
|
|
CASES: Final = (*NATIVE, *BRIDGES, *PARITY_CASES)
|
|
|
|
|
|
@pytest.mark.parametrize("case", CASES, ids=[case.id for case in CASES])
|
|
@pytest.mark.timeout(180)
|
|
def test_streamed_request_bills_the_same_row_as_the_non_streamed_request(
|
|
case: StreamParityTestCase, gateway: Gateway
|
|
) -> None:
|
|
assert_stream_parity(case, gateway)
|