mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-06 08:16:43 +00:00
4bae64e44a
* test(e2e): migrate access-control and inference-endpoint regression tests Move the access-control and non-chat inference-endpoint cases from litellm-regression-tests onto the shared e2e harness so a regression in either fails here first access_control/ asserts the gateway's authorization and error-shape contract: a key limited to one model is denied 403 (key_model_access_denied) when it calls another, a key scoped to allowed_routes=["llm_api_routes"] is forbidden 403 from a management route, and an unknown model is rejected 400 before any provider is called. The source asserted 401 for the disallowed-model case against an older proxy; the live contract is now a 403, so the guard tracks current behavior llm_translation/ gains one file per non-chat inference endpoint (/v1/responses, /v1/messages, /embeddings, /v1/rerank, /v1/audio/speech, /v1/images/generations). Each test registers the deployment it needs through /model/new, drives real provider traffic, asserts the parsed body carries real content instead of just a 200, then deletes the model on teardown, so nothing is hardcoded into the gateway config * Update endpoints_client.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
56 lines
1.6 KiB
Python
56 lines
1.6 KiB
Python
"""Client for the access-control e2e suite."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
from e2e_gateway import Gateway, build_gateway
|
|
from e2e_http import StreamingResponse
|
|
from models import (
|
|
ChatBody,
|
|
ChatMessage,
|
|
KeyGenerateBody,
|
|
LiteLLMParamsBody,
|
|
ModelInfoBody,
|
|
ModelNewBody,
|
|
)
|
|
|
|
MODEL_ACCESS_DENIED_MARKER = "key_model_access_denied"
|
|
ROUTE_NOT_ALLOWED_MARKER = "not allowed to call this route"
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class AccessControlClient:
|
|
gateway: Gateway
|
|
|
|
def llm_only_key(self) -> str:
|
|
return self.gateway.generate_key(
|
|
KeyGenerateBody(models=[], allowed_routes=["llm_api_routes"])
|
|
)
|
|
|
|
def delete_key(self, key: str) -> None:
|
|
self.gateway.delete_key(key)
|
|
|
|
def chat_status(self, key: str, model: str, content: str) -> StreamingResponse:
|
|
return self.gateway.transport.send(
|
|
"/chat/completions",
|
|
headers=self.gateway.transport.bearer(key),
|
|
json=ChatBody(
|
|
model=model, messages=[ChatMessage(role="user", content=content)]
|
|
),
|
|
)
|
|
|
|
def create_model_status(self, key: str, model_name: str) -> StreamingResponse:
|
|
return self.gateway.transport.send(
|
|
"/model/new",
|
|
headers=self.gateway.transport.bearer(key),
|
|
json=ModelNewBody(
|
|
model_name=model_name,
|
|
litellm_params=LiteLLMParamsBody(model="openai/gpt-4o-mini"),
|
|
model_info=ModelInfoBody(id=model_name),
|
|
),
|
|
)
|
|
|
|
|
|
def build_client() -> AccessControlClient:
|
|
return AccessControlClient(gateway=build_gateway())
|