mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-26 01:12:21 +00:00
10413796c6
* test(rust): group cache tests under cache/ and fold test_ocr.py into ocr/ The two failure cases in test_ocr.py duplicated the upstream-500 and timeout rows of PUBLIC_FAILURES, so only the file-input encoding case moves to ocr/test_requests.py Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(rust): split the response cache suite into one file per backend test_response_cache.py grew to 2400 lines. Each backend now has its own file, shared fixtures live in cache/conftest.py and shared helpers in support/cache.py. The helpers alias the private native test handles once, dropping the per-call reportPrivateUsage hits Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * split tokenizer test * test(core): consolidate route integration tests under tests/ with rstest and wiremock Moves the public-API OCR route tests out of src/ocr/route.rs and document.rs into tests/ocr/, split per provider plus lifecycle, machine, and document tests, merging the duplicated pairs. Messages, audio transcription, and chat completions share one wiremock-based upstream and recording secret source in tests/support, and gain table-driven cases for auth, routing, upstream errors, streaming, and declines. Tests of litellm-llms items move to that crate. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(messages): keep the stream relay test independent of the stream head contents The stream head carries no headers on main, so the relay test asserts the open-then-deliver order and the relayed body instead of header hand-off. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> --------- Co-authored-by: Yujong Lee <yujong@berri.ai> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
40 lines
1.5 KiB
Python
40 lines
1.5 KiB
Python
from typing import Final, Protocol
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
|
|
from litellm.caching.caching import Cache
|
|
from litellm.rust_bridge import _native, catalog
|
|
from litellm.rust_bridge.catalog import CacheRule
|
|
from litellm.rust_bridge.configuration import Rollout
|
|
from litellm.rust_bridge.response_cache import ResponseCacheRuntime
|
|
from litellm.types.caching import LiteLLMCacheType
|
|
|
|
CacheTestHandle: Final = _native._CacheTestHandle # pyright: ignore[reportPrivateUsage] # test-only handle has no public module name
|
|
|
|
|
|
CacheTestResolver: Final = _native._CacheTestResolver # pyright: ignore[reportPrivateUsage] # test-only resolver has no public module name
|
|
|
|
|
|
class CacheLookup(Protocol):
|
|
def get_cache(self, **kwargs: object) -> object: ...
|
|
def flush_cache(self) -> object: ...
|
|
|
|
|
|
def request(key: str = "key") -> dict[str, object]:
|
|
return {"key": {"preset": key}}
|
|
|
|
|
|
def require_rust(monkeypatch: pytest.MonkeyPatch, backend: LiteLLMCacheType) -> None:
|
|
monkeypatch.setattr(catalog, "RULES", (CacheRule(Rollout.RUST_REQUIRED, backends=frozenset({backend})),))
|
|
|
|
|
|
def assert_native_runtime(facade: Cache) -> ResponseCacheRuntime:
|
|
runtime: Final = facade._native_cache # pyright: ignore[reportPrivateUsage] # the activation under test has no public accessor
|
|
assert isinstance(runtime, ResponseCacheRuntime)
|
|
assert runtime.kind == "native"
|
|
return runtime
|
|
|
|
|
|
def completion_kwargs(label: str) -> dict[str, object]:
|
|
return {"model": "gpt-4o", "messages": [{"role": "user", "content": f"{label} {uuid4().hex}"}]}
|