mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-07 02:59:05 +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>
36 lines
1.3 KiB
Python
36 lines
1.3 KiB
Python
"""Live e2e: POST /v1/responses returns a real completion.
|
|
|
|
Registers an OpenAI deployment at runtime, drives the Responses API through the
|
|
gateway, and asserts output text came back. Migrated from
|
|
litellm-regression-tests/tests/test_inference_endpoints.py.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from e2e_config import unique_marker
|
|
from e2e_http import require_successful_call
|
|
from endpoints_client import EndpointsClient, ResponsesResult
|
|
from lifecycle import ResourceManager
|
|
from models import LiteLLMParamsBody
|
|
|
|
pytestmark = pytest.mark.e2e
|
|
|
|
|
|
class TestResponses:
|
|
def test_responses_returns_completion(
|
|
self, endpoints_client: EndpointsClient, resources: ResourceManager
|
|
) -> None:
|
|
model = f"e2e-responses-{unique_marker()}"
|
|
model_id = endpoints_client.create_model(
|
|
model,
|
|
LiteLLMParamsBody(model="openai/gpt-4o-mini", api_key="os.environ/OPENAI_API_KEY"),
|
|
)
|
|
resources.defer(lambda: endpoints_client.delete_model(model_id))
|
|
key = resources.key()
|
|
|
|
result = endpoints_client.responses(key, model, "reply with one word")
|
|
require_successful_call(result)
|
|
parsed = ResponsesResult.model_validate_json(result.body)
|
|
assert parsed.text.strip(), f"/responses returned no output text: {result.body[:300]}"
|