mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-11 22:51:28 +00:00
ad79b314c5
* test(e2e): cover legacy text /completions endpoint The /completions (and /v1/completions) text-completion route had zero e2e coverage despite being the second-busiest endpoint in production; everything 'completions' in the suite was chat. Add a text-completion endpoint test that registers an OpenAI instruct deployment, drives /v1/completions through the gateway, and asserts real generated text. Adds text_completions() + the completion request/result models to EndpointsClient, the 'completions' endpoint to the coverage registry vocab, and the registry cell. * test(e2e): assert /v1/completions choices shape, not just joined text Assert the response carries a choices array and the first choice has real text, so a malformed response (no choices) and a clean-but-empty completion are distinct failures. Drop the unused text property / id / model fields (model only what the test reads).
46 lines
1.9 KiB
Python
46 lines
1.9 KiB
Python
"""Live e2e: POST /v1/completions returns a real text completion.
|
|
|
|
The legacy text-completion endpoint (prompt-style, non-chat) is the second-busiest
|
|
route in production yet was previously uncovered; the rest of the "completions"
|
|
surface is chat only. Registers an OpenAI instruct deployment at runtime (deleted
|
|
on teardown), drives /v1/completions through the gateway, and asserts real
|
|
generated text came back so a regression that empties the completion fails here.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from e2e_config import unique_marker
|
|
from e2e_http import require_successful_call
|
|
from endpoints_client import CompletionsResult, EndpointsClient
|
|
from lifecycle import ResourceManager
|
|
from models import LiteLLMParamsBody
|
|
|
|
pytestmark = pytest.mark.e2e
|
|
|
|
|
|
class TestCompletionsEndpoint:
|
|
@pytest.mark.covers("llm.completions.openai.basic.nonstream.works")
|
|
def test_text_completion_returns_text(
|
|
self, endpoints_client: EndpointsClient, resources: ResourceManager
|
|
) -> None:
|
|
model = f"e2e-completions-{unique_marker()}"
|
|
model_id = endpoints_client.create_model(
|
|
model,
|
|
LiteLLMParamsBody(
|
|
model="text-completion-openai/gpt-3.5-turbo-instruct",
|
|
api_key="os.environ/OPENAI_API_KEY",
|
|
),
|
|
)
|
|
resources.defer(lambda: endpoints_client.delete_model(model_id))
|
|
key = resources.key()
|
|
|
|
result = endpoints_client.text_completions(
|
|
key, model, "Finish this sentence in a few words: the capital of France is"
|
|
)
|
|
require_successful_call(result)
|
|
parsed = CompletionsResult.model_validate_json(result.body)
|
|
assert parsed.choices, f"/v1/completions returned no choices: {result.body[:300]}"
|
|
completion = (parsed.choices[0].text or "").strip()
|
|
assert completion, f"/v1/completions returned an empty completion: {result.body[:300]}"
|