mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-02 02:11:58 +00:00
6fd9334751
* feat(tracing): bring current ingestion prerequisite onto main
Port the prerequisite implementation from BerriAI/litellm#43915 at 5aacd57455 so Lens does not depend on the retired tracing stack.
* feat(lens): add trace analysis and standalone worker
* fix(lens): clarify review limits and finalize main integration
* fix(lens): simplify worker setup and show the next check
* fix(lens): simplify analyzer setup and resolve integration failures
* fix(lens): preserve durations and evidence from later trace reads
* fix(lens): trust server context for internal analysis exclusion
* fix(lens): pin reviewed analyzer image and verify request inclusion
* test(lens): select time units before entering custom duration
* test(lens): allow the standalone analyzer lifetime HTTP client
* test(lens): run analyzer tests in active proxy coverage shard
19 lines
714 B
Python
19 lines
714 B
Python
from typing import Final
|
|
|
|
import pytest
|
|
|
|
from litellm.proxy.engine.inference import Deployment, DeploymentParams, completion_charge, quote
|
|
from litellm.types.utils import ModelResponse
|
|
|
|
|
|
def test_custom_priced_model_charges_reported_tokens() -> None:
|
|
deployment: Final = Deployment(
|
|
litellm_params=DeploymentParams(
|
|
model="openai/engine-test", input_cost_per_token=0.001, output_cost_per_token=0.002
|
|
)
|
|
)
|
|
response: Final = ModelResponse(
|
|
model="engine-test", usage={"prompt_tokens": 20, "completion_tokens": 10, "total_tokens": 30}
|
|
)
|
|
assert completion_charge((deployment,), response, 10) == pytest.approx(0.04)
|
|
assert quote((deployment,), "hello") > 0.04
|