mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-17 09:34:48 +00:00
test(router): type the default-endpoint boundary test helpers
This commit is contained in:
parent
56e3dec351
commit
243f6fd3c3
1 changed files with 10 additions and 7 deletions
|
|
@ -16,6 +16,7 @@ The mechanism works without any cache and supports two encoding strategies:
|
|||
"""
|
||||
|
||||
import time
|
||||
from collections.abc import Mapping
|
||||
from typing import Final
|
||||
from unittest.mock import AsyncMock, patch
|
||||
|
||||
|
|
@ -2717,12 +2718,14 @@ async def test_affinity_keeps_reasoning_when_every_deployment_already_refused_th
|
|||
assert reasoning_input[0] == original_reasoning
|
||||
|
||||
|
||||
def _default_endpoint_deployment(model_id: str, litellm_params: dict[str, object]) -> dict[str, object]:
|
||||
return {"model_name": "gpt-5.5", "litellm_params": litellm_params, "model_info": {"id": model_id}}
|
||||
def _default_endpoint_deployment(model_id: str, litellm_params: Mapping[str, object]) -> dict[str, object]:
|
||||
return {"model_name": "gpt-5.5", "litellm_params": dict(litellm_params), "model_info": {"id": model_id}}
|
||||
|
||||
|
||||
def _deployment_of(router: litellm.Router, model_id: str) -> dict[str, object]:
|
||||
return next(deployment for deployment in router.model_list if deployment["model_info"]["id"] == model_id)
|
||||
deployment: Final = router.get_deployment(model_id=model_id)
|
||||
assert deployment is not None
|
||||
return deployment.model_dump(exclude_none=True)
|
||||
|
||||
|
||||
SUMMARY_ONLY_REASONING: Final = {"type": "reasoning", "summary": [{"type": "summary_text", "text": "scattering"}]}
|
||||
|
|
@ -2840,16 +2843,16 @@ async def test_affinity_pins_to_the_same_key_peer_on_the_default_endpoint_when_t
|
|||
_default_endpoint_deployment("other-org", {**OPENAI_SHARED_KEY, "api_key": "other-key"}),
|
||||
]
|
||||
)
|
||||
healthy: Final = [_deployment_of(router, "peer"), _deployment_of(router, "other-org")]
|
||||
peer: Final = _deployment_of(router, "peer")
|
||||
reasoning_input: Final = _reasoning_input_minted_by("origin")
|
||||
original_reasoning: Final = dict(reasoning_input[0])
|
||||
|
||||
result: Final = await EncryptedContentAffinityCheck(router=router).async_filter_deployments(
|
||||
result: Final[list[dict[str, object]]] = await EncryptedContentAffinityCheck(router=router).async_filter_deployments(
|
||||
model="gpt-5.5",
|
||||
healthy_deployments=healthy,
|
||||
healthy_deployments=[peer, _deployment_of(router, "other-org")],
|
||||
messages=None,
|
||||
request_kwargs={"litellm_metadata": {}, "input": reasoning_input},
|
||||
)
|
||||
|
||||
assert [deployment["model_info"]["id"] for deployment in result] == ["peer"]
|
||||
assert result == [peer]
|
||||
assert reasoning_input[0] == original_reasoning
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue