mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-11 08:38:24 +00:00
3f38730d2c
* refactor(typing): clear basedpyright Any errors (wave 1) * refactor(typing): clear basedpyright Any errors (wave 2) * refactor(typing): clear basedpyright Any errors (wave 3) * refactor(typing): clear basedpyright Any errors (wave 4) * refactor(typing): clear basedpyright Any errors (wave 5) * refactor(typing): clear basedpyright Any errors (wave 6) * fix(typing): keep the cached-plan fallback's direct query_first calls so span naming resolves * fix(logging): keep callbacks running when litellm_params is a params model should_run_callback and the sync success and failure handlers read litellm_params through any object with a get method again, as they did before this branch, so a logging hook that returns a GenericLiteLLMParams no longer stops sync logging for that request Adds behavior tests for the changed lines codecov listed as not run * fix: read the regional uplift for every data residency again and reuse one dict TypeAdapter The typed lookup only read the eu and us multipliers, so a deployment that set regional_processing_uplift_multiplier_fedramp stopped applying it. /model/update and the model write paths now share one module-level TypeAdapter instead of building one per call. * fix: bill regional uplift multipliers float() accepts, bytes included * fix: raise the in operator's own error from one shared json_contains, and name the bad uplift type
90 lines
2.8 KiB
Python
90 lines
2.8 KiB
Python
import importlib.util
|
|
import sys
|
|
from collections.abc import Mapping, Sequence
|
|
from dataclasses import dataclass
|
|
from types import ModuleType, SimpleNamespace
|
|
from typing import Final
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
import respx
|
|
|
|
import litellm
|
|
from litellm import completion
|
|
|
|
|
|
def test_wandb_logging():
|
|
try:
|
|
response = completion(
|
|
model="claude-3-5-haiku-20241022",
|
|
messages=[{"role": "user", "content": "Hi 👋 - i'm claude"}],
|
|
max_tokens=10,
|
|
temperature=0.2,
|
|
)
|
|
print(response)
|
|
except litellm.Timeout as e:
|
|
pass
|
|
except Exception as e:
|
|
print(e)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class _TraceResult:
|
|
inputs: Mapping[str, object]
|
|
outputs: Mapping[str, object]
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class _TraceSpan:
|
|
name: str
|
|
attributes: Mapping[str, object]
|
|
start_time_ms: int
|
|
end_time_ms: int
|
|
span_kind: str
|
|
results: Sequence[_TraceResult]
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class _TraceTree:
|
|
root_span: _TraceSpan
|
|
model_dict: Mapping[str, object]
|
|
|
|
|
|
def _weights_biases_with_stub_trace_tree(monkeypatch: pytest.MonkeyPatch) -> ModuleType:
|
|
data_types: Final = ModuleType("wandb.sdk.data_types")
|
|
data_types.trace_tree = SimpleNamespace(
|
|
Result=_TraceResult, Span=_TraceSpan, WBTraceTree=_TraceTree, SpanKind=SimpleNamespace(LLM="LLM")
|
|
)
|
|
for name in ("wandb", "wandb.sdk"):
|
|
monkeypatch.setitem(sys.modules, name, ModuleType(name))
|
|
monkeypatch.setitem(sys.modules, "wandb.sdk.data_types", data_types)
|
|
spec: Final = importlib.util.find_spec("litellm.integrations.weights_biases")
|
|
assert spec is not None and spec.loader is not None
|
|
module: Final = importlib.util.module_from_spec(spec)
|
|
monkeypatch.setitem(sys.modules, spec.name, module)
|
|
spec.loader.exec_module(module)
|
|
return module
|
|
|
|
|
|
def test_wandb_chat_completion_trace_lists_each_request_message_with_its_role(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
weights_biases: Final = _weights_biases_with_stub_trace_tree(monkeypatch)
|
|
request: Final = {
|
|
"model": "gpt-4o",
|
|
"messages": [{"role": "system", "content": "Be brief."}, {"role": "user", "content": "Hi"}],
|
|
}
|
|
response: Final = {
|
|
"object": "chat.completion",
|
|
"model": "gpt-4o",
|
|
"created": 1767225600,
|
|
"choices": [{"message": {"role": "assistant", "content": "Hello!"}}],
|
|
}
|
|
|
|
trace: Final = weights_biases.OpenAIRequestResponseResolver()(request, response, 1.5)
|
|
|
|
assert trace.root_span.results == [
|
|
_TraceResult(
|
|
inputs={"request": "\n\n**system**: Be brief.\n\n\n**user**: Hi\n"},
|
|
outputs={"response": "\n\n**assistant**: Hello!\n"},
|
|
)
|
|
]
|
|
assert trace.root_span.end_time_ms - trace.root_span.start_time_ms == 1500
|