litellm/tests/unit/rust_bridge/ocr/test_secrets.py
yuneng-jiang a11a93f44a
test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)
* ci: run the unit_selection.sh shard files on every event instead of only fork pull requests

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* ci: rename fork-flag to unit-flag now that it applies on every event

* test: move tests/test_litellm root and small trees into tests/unit

Pure renames, no content changes. Follow-up commits in this PR fix
references, merge the three files that already existed in tests/unit,
keep live-provider tests in tests/test_litellm and wire CI.

* test: carry tests/test_litellm conftest isolation into tests/unit

Callback lists, routing fallbacks, cached HTTP clients, logger state, AWS,
proxy-URL and keychain env, and session-end client cleanup now reset for
unit tests too. The environment isolation owns its MonkeyPatch so a test's
own monkeypatch is undone before the model-cost teardown runs.

* test: merge, split and prune the moved root and small-tree tests

Merge batches/test_batch_utils.py and the chat_completions and messages
dispatch tests into the files that already existed in tests/unit. Keep
the live Gemini interactions tests, the async image-fetch format test and
the OpenAI embedding scorer test in tests/test_litellm since they need
real network or keys. Put test_router.py under tests/unit/test_router so
the existing package no longer shadows it. Delete eight tests the audit
found superseded by stronger ones kept in this move.

* ci: run the moved root and small-tree tests under their legacy flags

Add the misc and responses-caching-types flags to unit_selection.sh and
CircleCI, extend enterprise-routing and mcp-integration, and point the
legacy GHA shards, Makefile, redis-compat workflow, merge smoke manifest
and change classifier at the new paths.

* test: make the new tests/unit directories packages

tests/unit/test_package_layout.py requires every directory to carry an
__init__.py, and without one the moved and retained
test_litellm_responses_bridge.py modules collide on import.

* test: scope the unit socket block to tests/unit in shared sessions

The GHA shards collect the legacy test-path and the unit selection in one
pytest session. The unit conftest's loopback-only block leaked into legacy
modules that reach the network at import. The legacy conftest now lifts the
restriction at collect and setup time, and the unit conftest re-applies it
when collecting its own modules.

* test: move tests/test_litellm/llms into tests/unit/llms

Rename-only. Moves the provider tests and the fine-tuning fixtures they
load, mirroring the old paths. Follow-up commits merge, split and wire them.

* test: merge, split and prune the moved llms tests

Merges the Databricks chat transformation tests into the existing unit
file, keeps the tests that need real keys or the network in
tests/test_litellm, deletes the audited tests a stronger unit test
already covers, and points imports at tests.unit.llms.

* ci: run the moved llms tests under their legacy flags

The Vertex AI and All Other Providers shards keep their legacy test-path
for the retained files and add the llm-vertex-ai and llm-other-providers
unit selections. CircleCI gets matching unit jobs.

* test: make the tests/unit/llms directories packages

Adds __init__.py to the moved dirs and drops the legacy ones whose
directories no longer hold tests.

* test: drop script runners and path hacks the llms split left dangling

The __main__ runners in the split openai_like files and the Databricks e2e
runner called tests that now live in the other half of the split or were
deleted. The retained legacy halves also no longer need sys.path edits.

* test: give the shard-script tests their own GITHUB_OUTPUT

They only passed where the runner set it. The CircleCI unit job's env
allowlist drops it, so the script's redirect failed there.

* test: point the router and module-deletion checks at tests/unit

router_code_coverage and code_qa_check_tests only searched tests/test_litellm,
so the moved router tests no longer counted. The two silent-experiment tests
the audit deleted were the only direct callers of those methods; they are
replaced with tests that assert the forwarded shadow request and the
recursion guard.

* test: move tests/test_litellm integrations and secret_managers into tests/unit

Rename-only. Mirrors the old paths, including the directory conftests
and the prompt and JSON fixtures. Follow-up commits prune and wire them.

* test: prune and repoint the moved integrations tests

Deletes the 7 audited tests a stronger test in the same tree already
covers, imports the TLS sink helpers from their new conftest path, and
restores os.environ after each integrations test. Some presets write
OTEL_EXPORTER_OTLP_HEADERS straight into os.environ, and without the
legacy tree's test ordering that header leaked into the AgentOps tests.

* ci: run the moved integrations tests under their legacy flag

The integrations GHA shard and a new CircleCI job run the integrations
unit selection. secret_managers joins the misc selection.

* docs: point integrations and secret_managers references at tests/unit

* test: make the moved integrations directories packages

* test: keep the Databricks manual e2e runner and fix the SageMaker Nova run path

The Databricks e2e file is a manual script whose main() calls the tests
that were pruned, so pruning them broke the documented run. It is back to
its main version. The SageMaker Nova docstring now points at the file's
real location in tests/local_testing.

* test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit

Rename-only. Mirrors the old paths, including fixtures, the stubtest config
and the native-route wheel script. Two files that collide with existing unit
files are merged in a follow-up commit.

* test: merge, prune and repoint the moved core, routing, responses, caching and rust_bridge tests

Merges the two files that collided with existing unit files, folding the
legacy extra case into test_is_chat_completion_cached_dict, and deletes the
9 audited tests a stronger test in the same file already covers.

Keeps what needs the network in tests/test_litellm: test_tokenizers pulls a
tokenizer from the Hugging Face hub, and the gpt2 and r50k_base tokenizer
cases download their BPE files. The unit core_utils conftest points
TIKTOKEN_CACHE_DIR at litellm's bundled encodings so the rest never depend on
import order to stay offline, and FakeSecretVault moves to a shared module
so both trees can build it.

* ci: run the moved core, routing, responses, caching and rust_bridge tests under their flags

core_utils gets a core-utils flag and CircleCI job, and its GHA shard keeps
the legacy path for the retained network tests. router_utils and
router_strategy join enterprise-routing, responses joins
responses-caching-types (minus responses/mcp, which mcp-integration owns),
caching joins caching-local and rust_bridge joins misc. The redis-compat,
test-rust, stubtest and merge-smoke paths follow the move.

* docs: point the Rust crate references at tests/unit

* test: make the moved core, routing and rust_bridge directories packages

* test: keep the no-loop DualCache batch_get_cache regression test

It runs the sync path outside any event loop, which the inside-loop test
cannot, so a change that picks the Redis client by loop state would only
show up there.

* test: keep the job's UNIT_FLAG out of the shard-script tests

* fix(url_utils): block 192.0.0.0/24 on every Python patch release

* test: move the new budget limiter tests into tests/unit/router_strategy

* test: move the new sentry scrubbing tests into tests/unit/litellm_core_utils

* test: move the new zerobus tests into tests/unit/integrations

* test: make tests/unit/integrations/zerobus a package

* test: load litellm's own tiktoken cache setup once instead of resetting it per test

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-25 17:10:13 -07:00

467 lines
18 KiB
Python

from __future__ import annotations
import asyncio
from collections.abc import Awaitable, Generator, Mapping
from contextlib import contextmanager
from dataclasses import replace
from types import MappingProxyType
from typing import Final, Literal, Protocol, TypeAlias, cast
import httpx
import pytest
import litellm
from litellm.integrations.custom_secret_manager import CustomSecretManager
from litellm.llms.base_llm.ocr.transformation import OCRResponse
from litellm.rust_bridge import settings
from litellm.rust_bridge.ocr.entrypoints import NATIVE_AOCR, NATIVE_OCR, LiteLLMOcrRequest
from litellm.types.secret_managers.main import KeyManagementSettings, KeyManagementSystem
from tests.test_litellm_rust.support.recording_server import RecordingServer, ResponseSpec, recording_service
from tests.test_litellm_rust.support.requests import OCR_DOCUMENT, OCR_MODEL, OCR_RESPONSE
native: Final = pytest.importorskip("litellm.rust_bridge._native")
AccessMode: TypeAlias = Literal["read_only", "write_only", "read_and_write"]
class Ocr(Protocol):
def __call__(self, api_base: str, /) -> Awaitable[OCRResponse]: ...
class _VaultSecrets(CustomSecretManager):
def __init__(self, failure: BaseException | None = None) -> None:
super().__init__(secret_manager_name="rust_bridge_ocr_test")
self.failure: Final = failure
self.reads: tuple[tuple[str, Mapping[str, object] | None], ...] = ()
async def async_read_secret(
self,
secret_name: str,
optional_params: dict[str, object] | None = None,
timeout: float | httpx.Timeout | None = None,
) -> str | None:
raise AssertionError("get_secret reads custom managers synchronously")
def sync_read_secret(
self,
secret_name: str,
optional_params: dict[str, object] | None = None,
timeout: float | httpx.Timeout | None = None,
) -> str | None:
self.reads = (*self.reads, (secret_name, optional_params))
if secret_name != "MISTRAL_API_KEY":
return None
if self.failure is not None:
raise self.failure
return "vault-key"
def key_reads(self) -> tuple[Mapping[str, object] | None, ...]:
return tuple(params for name, params in self.reads if name == "MISTRAL_API_KEY")
def _native_request(api_base: str) -> LiteLLMOcrRequest:
return LiteLLMOcrRequest(
model=OCR_MODEL,
document=OCR_DOCUMENT,
api_key=None,
api_base=api_base,
timeout=None,
custom_llm_provider=None,
extra_headers=None,
kwargs=MappingProxyType({}),
)
def _public_kwargs(api_base: str) -> dict[str, object]:
return {"model": OCR_MODEL, "document": OCR_DOCUMENT, "api_base": api_base}
async def _rust_ocr(api_base: str) -> OCRResponse:
route: Final = NATIVE_OCR.load()
assert route is not None
return route(_native_request(api_base), (), _public_kwargs(api_base))
async def _rust_aocr(api_base: str) -> OCRResponse:
route: Final = NATIVE_AOCR.load()
assert route is not None
return await route(_native_request(api_base), (), _public_kwargs(api_base))
_RUST_PATHS: Final = (_rust_ocr, _rust_aocr)
_RUST_IDS: Final = ("rust-sync", "rust-async")
@pytest.fixture(params=_RUST_PATHS, ids=_RUST_IDS)
def ocr(request: pytest.FixtureRequest) -> Ocr:
return cast(Ocr, request.param)
@pytest.fixture(params=_RUST_PATHS, ids=_RUST_IDS)
def rust_ocr(request: pytest.FixtureRequest) -> Ocr:
return cast(Ocr, request.param)
@contextmanager
def _mistral_service(expected_requests: int = 1) -> Generator[RecordingServer]:
with recording_service() as server:
server.default_response = ResponseSpec(body=OCR_RESPONSE)
server.expected_requests = expected_requests
yield server
def _configure(
monkeypatch: pytest.MonkeyPatch,
*,
manager: _VaultSecrets,
key_management: KeyManagementSettings,
native_secret_manager: bool = True,
environment_key: str | None = "environment-key",
) -> None:
if environment_key is None:
monkeypatch.delenv("MISTRAL_API_KEY", raising=False)
else:
monkeypatch.setenv("MISTRAL_API_KEY", environment_key)
monkeypatch.setattr(litellm, "secret_manager_client", manager)
monkeypatch.setattr(litellm, "_key_management_system", KeyManagementSystem.CUSTOM)
monkeypatch.setattr(litellm, "_key_management_settings", key_management)
configured: Final = settings.secret_manager
monkeypatch.setattr(settings, "secret_manager", lambda: replace(configured(), native=native_secret_manager))
@pytest.mark.parametrize(
("access_mode", "hosted_keys"),
(("read_only", None), ("read_and_write", None), ("read_only", ["MISTRAL_API_KEY"])),
)
async def test_custom_secret_manager_supplies_the_ocr_key(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr, access_mode: AccessMode, hosted_keys: list[str] | None
) -> None:
manager: Final = _VaultSecrets()
key_management: Final = KeyManagementSettings(access_mode=access_mode, hosted_keys=hosted_keys)
_configure(monkeypatch, manager=manager, key_management=key_management)
with _mistral_service() as server:
await ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer vault-key"
assert manager.key_reads(), "the custom manager was never asked for MISTRAL_API_KEY"
assert all(params == key_management.model_dump() for params in manager.key_reads()), manager.key_reads()
@pytest.mark.parametrize(("access_mode", "hosted_keys"), (("read_only", ["OTHER"]), ("write_only", None)))
async def test_custom_secret_manager_is_not_read_when_settings_exclude_the_key(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr, access_mode: AccessMode, hosted_keys: list[str] | None
) -> None:
manager: Final = _VaultSecrets()
_configure(
monkeypatch,
manager=manager,
key_management=KeyManagementSettings(access_mode=access_mode, hosted_keys=hosted_keys),
)
with _mistral_service() as server:
await ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer environment-key"
assert manager.key_reads() == ()
async def test_custom_secret_manager_exceptions_fall_back_to_the_environment_key(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr
) -> None:
_configure(
monkeypatch,
manager=_VaultSecrets(ValueError("secret manager failed")),
key_management=KeyManagementSettings(access_mode="read_only"),
)
with _mistral_service() as server:
await ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer environment-key"
async def test_custom_secret_manager_exceptions_without_environment_key_raise_missing_key(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr
) -> None:
_configure(
monkeypatch,
manager=_VaultSecrets(ValueError("secret manager failed")),
key_management=KeyManagementSettings(access_mode="read_only"),
environment_key=None,
)
with _mistral_service(expected_requests=0) as server:
with pytest.raises(litellm.APIConnectionError, match="Missing Mistral API Key"):
await ocr(server.base_url)
async def test_custom_secret_manager_cancellation_propagates_without_provider_io(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr
) -> None:
failure: Final = asyncio.CancelledError("secret manager cancelled")
_configure(
monkeypatch, manager=_VaultSecrets(failure), key_management=KeyManagementSettings(access_mode="read_only")
)
with _mistral_service(expected_requests=0) as server:
with pytest.raises(asyncio.CancelledError) as raised:
await ocr(server.base_url)
assert raised.value is failure
async def test_rust_reads_a_python_only_secret_manager_through_python(
monkeypatch: pytest.MonkeyPatch, rust_ocr: Ocr
) -> None:
manager: Final = _VaultSecrets()
key_management: Final = KeyManagementSettings(access_mode="read_only")
_configure(monkeypatch, manager=manager, key_management=key_management, native_secret_manager=False)
with _mistral_service() as server:
await rust_ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer vault-key"
assert manager.key_reads(), "the Python manager was never asked for MISTRAL_API_KEY"
assert all(params == key_management.model_dump() for params in manager.key_reads()), manager.key_reads()
class _PythonManagerReads:
def __init__(self) -> None:
self.reads: tuple[tuple[object, str, str], ...] = ()
def __call__(
self,
client: object,
key_manager: str,
secret_name: str,
key_management_settings: KeyManagementSettings | None = None,
) -> str | None:
self.reads = (*self.reads, (client, key_manager, secret_name))
return "python-key" if secret_name == "MISTRAL_API_KEY" else None
async def test_python_only_builtin_manager_is_read_through_python_not_its_native_backend(
monkeypatch: pytest.MonkeyPatch, rust_ocr: Ocr
) -> None:
from litellm.secret_managers import main as secret_manager_main
from litellm.secret_managers.aws_secret_manager_v2 import AWSSecretsManagerV2
python_reads: Final = _PythonManagerReads()
monkeypatch.setattr(secret_manager_main, "get_secret_from_manager", python_reads)
monkeypatch.setenv("AWS_ACCESS_KEY_ID", "native-access")
monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "native-secret")
monkeypatch.delenv("MISTRAL_API_KEY", raising=False)
manager: Final = AWSSecretsManagerV2(aws_region_name="us-east-1")
monkeypatch.setattr(litellm, "secret_manager_client", manager)
monkeypatch.setattr(litellm, "_key_management_system", KeyManagementSystem.AWS_SECRET_MANAGER)
monkeypatch.setattr(litellm, "_key_management_settings", KeyManagementSettings(hosted_keys=["MISTRAL_API_KEY"]))
monkeypatch.setattr(settings, "secret_manager", lambda: settings.SecretManager(readable=True, native=False))
with _mistral_service() as provider:
await rust_ocr(provider.base_url)
assert provider.requests[0].headers["authorization"] == "Bearer python-key"
assert (manager, "aws_secret_manager", "MISTRAL_API_KEY") in python_reads.reads
assert getattr(manager, "_litellm_native_secret_manager", None) is None
async def test_no_secret_client_leaves_dormant_binding_settings_unread(
monkeypatch: pytest.MonkeyPatch, rust_ocr: Ocr
) -> None:
monkeypatch.setenv("MISTRAL_API_KEY", "environment-key")
monkeypatch.setattr(litellm, "secret_manager_client", None)
monkeypatch.setattr(litellm, "_key_management_settings", object())
with _mistral_service() as server:
await rust_ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer environment-key"
class _FixedSecrets(CustomSecretManager):
def __init__(self, value: str) -> None:
super().__init__(secret_manager_name="rust_bridge_ocr_fixed")
self.value: Final = value
async def async_read_secret(
self,
secret_name: str,
optional_params: dict[str, object] | None = None,
timeout: float | httpx.Timeout | None = None,
) -> str | None:
raise AssertionError("get_secret reads custom managers synchronously")
def sync_read_secret(
self,
secret_name: str,
optional_params: dict[str, object] | None = None,
timeout: float | httpx.Timeout | None = None,
) -> str | None:
return self.value if secret_name == "MISTRAL_API_KEY" else None
class _PlainSecretReader:
def sync_read_secret(
self,
secret_name: str,
optional_params: dict[str, object] | None = None,
timeout: float | httpx.Timeout | None = None,
) -> str | None:
return "vault-key"
class _AzureSecret:
def __init__(self, value: str | None) -> None:
self.value: Final = value
def _azure_sdk_client(value: str | None) -> object:
class SecretClient:
def get_secret(self, name: str) -> _AzureSecret:
return _AzureSecret(value if name == "MISTRAL_API_KEY" else None)
SecretClient.__module__ = "azure.keyvault.secrets._client"
return SecretClient()
def _configure_client(
monkeypatch: pytest.MonkeyPatch,
*,
client: object,
system: KeyManagementSystem,
key_management: KeyManagementSettings,
environment_key: str = "environment-key",
) -> None:
monkeypatch.setenv("MISTRAL_API_KEY", environment_key)
monkeypatch.setattr(litellm, "secret_manager_client", client)
monkeypatch.setattr(litellm, "_key_management_system", system)
monkeypatch.setattr(litellm, "_key_management_settings", key_management)
configured: Final = settings.secret_manager
monkeypatch.setattr(settings, "secret_manager", lambda: replace(configured(), native=True))
async def _assert_missing_key(ocr: Ocr) -> None:
with _mistral_service(expected_requests=0) as server:
with pytest.raises(litellm.APIConnectionError, match="Missing Mistral API Key"):
await ocr(server.base_url)
@pytest.mark.parametrize("environment_key", ("true", " FALSE ", "True"))
async def test_boolean_environment_keys_count_as_missing(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr, environment_key: str
) -> None:
monkeypatch.setenv("MISTRAL_API_KEY", environment_key)
monkeypatch.setattr(litellm, "secret_manager_client", None)
await _assert_missing_key(ocr)
@pytest.mark.parametrize("manager_key", ("True", "(False)"))
async def test_boolean_manager_keys_count_as_missing(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr, manager_key: str
) -> None:
_configure_client(
monkeypatch,
client=_FixedSecrets(manager_key),
system=KeyManagementSystem.CUSTOM,
key_management=KeyManagementSettings(access_mode="read_only"),
)
await _assert_missing_key(ocr)
async def test_boolean_environment_fallback_after_a_manager_exception_counts_as_missing(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr
) -> None:
_configure(
monkeypatch,
manager=_VaultSecrets(ValueError("secret manager failed")),
key_management=KeyManagementSettings(access_mode="read_only"),
environment_key="True",
)
await _assert_missing_key(ocr)
async def test_manager_without_the_key_does_not_fall_back_to_the_environment(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr
) -> None:
_configure_client(
monkeypatch,
client=_azure_sdk_client(None),
system=KeyManagementSystem.AZURE_KEY_VAULT,
key_management=KeyManagementSettings(access_mode="read_only"),
)
await _assert_missing_key(ocr)
async def test_rust_hosted_keys_exclude_azure_sdk_clients_too(monkeypatch: pytest.MonkeyPatch, rust_ocr: Ocr) -> None:
_configure_client(
monkeypatch,
client=_azure_sdk_client("vault-key"),
system=KeyManagementSystem.AZURE_KEY_VAULT,
key_management=KeyManagementSettings(access_mode="read_only", hosted_keys=["OTHER"]),
)
with _mistral_service() as server:
await rust_ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer environment-key", (
"recorded divergence: Python's get_secret_from_manager recognizes Azure SDK clients by type and ignores hosted_keys"
)
async def test_custom_system_with_a_foreign_client_falls_back_to_the_environment(
monkeypatch: pytest.MonkeyPatch, ocr: Ocr
) -> None:
_configure_client(
monkeypatch,
client=_PlainSecretReader(),
system=KeyManagementSystem.CUSTOM,
key_management=KeyManagementSettings(access_mode="read_only"),
)
with _mistral_service() as server:
await ocr(server.base_url)
assert server.requests[0].headers["authorization"] == "Bearer environment-key"
async def test_native_backend_supplies_ocr_credentials_without_a_python_reader(
monkeypatch: pytest.MonkeyPatch, rust_ocr: Ocr
) -> None:
from litellm.secret_managers import main as secret_manager_main
from litellm.secret_managers import secret_manager_handler
from litellm.secret_managers.aws_secret_manager_v2 import AWSSecretsManagerV2
def reject_python_read(
client: object,
key_manager: str,
secret_name: str,
key_management_settings: KeyManagementSettings | None = None,
) -> str | None:
raise AssertionError("Rust must read the native backend directly")
monkeypatch.setattr(secret_manager_handler, "get_secret_from_manager", reject_python_read)
monkeypatch.setattr(secret_manager_main, "get_secret_from_manager", reject_python_read)
with recording_service() as secrets, _mistral_service(expected_requests=2) as provider:
secrets.default_response = ResponseSpec(body={"SecretString": "native-key"})
secrets.expected_requests = None
monkeypatch.setenv("AWS_ACCESS_KEY_ID", "native-access")
monkeypatch.setenv("AWS_SECRET_ACCESS_KEY", "native-secret")
monkeypatch.setenv("AWS_BEDROCK_RUNTIME_ENDPOINT", secrets.base_url)
monkeypatch.delenv("MISTRAL_API_KEY", raising=False)
manager: Final = AWSSecretsManagerV2(aws_region_name="us-east-1")
monkeypatch.setattr(litellm, "secret_manager_client", manager)
monkeypatch.setattr(litellm, "_key_management_system", KeyManagementSystem.AWS_SECRET_MANAGER)
monkeypatch.setattr(litellm, "_key_management_settings", KeyManagementSettings(hosted_keys=["MISTRAL_API_KEY"]))
monkeypatch.setattr(settings, "secret_manager", lambda: settings.SecretManager(readable=True, native=True))
await rust_ocr(provider.base_url)
await rust_ocr(provider.base_url)
assert len(secrets.requests) == 2, [(request.path, request.body) for request in secrets.requests]
assert all(request.headers["authorization"] == "Bearer native-key" for request in provider.requests)
assert all("Credential=native-access/" in request.headers["authorization"] for request in secrets.requests)
assert native._SecretManagerRuntime.from_client(manager) is getattr(manager, "_litellm_native_secret_manager")