Skip to content

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Rust

fix: normalize empty content-filter responses instead of raising (#358)

Andrew Whitefa006f2632b3
diff --git a/examples/experimental/litellm/src/switchyard_litellm/client.py b/examples/experimental/litellm/src/switchyard_litellm/client.py
index dd83b5b0a..277fbe6fa 100644
--- a/examples/experimental/litellm/src/switchyard_litellm/client.py
+++ b/examples/experimental/litellm/src/switchyard_litellm/client.py
@@ -300,7 +300,7 @@ def _response(response: ModelResponse) -> dict[str, object]:
"name": tool_call.function.name,
"arguments": arguments,
})
- if not content:
+ if not content and choice.finish_reason != "content_filter":
raise ValueError("LiteLLM returned no text content")
return {
"id": response.id,
diff --git a/examples/experimental/litellm/tests/test_client.py b/examples/experimental/litellm/tests/test_client.py
index 157b35c05..0f7e6555a 100644
--- a/examples/experimental/litellm/tests/test_client.py
+++ b/examples/experimental/litellm/tests/test_client.py
@@ -15,6 +15,7 @@ from litellm import (
from litellm.exceptions import (
ContextWindowExceededError as LiteLLMContextWindowExceededError,
)
+from litellm.types.utils import Choices, Message, Usage
from switchyard_litellm import LiteLLMSyClient
from switchyard.libsy import ContextWindowExceededError
@@ -582,3 +583,46 @@ async def test_cached_token_count_preserves_explicit_zero() -> None:
await client.aclose()
assert response["usage"]["cached_input_tokens"] == 0
+
+
+def test_response_content_filter_empty_content() -> None:
+ """Empty content with a content_filter finish reason must be normalized."""
+ from switchyard_litellm.client import _response
+
+ response = ModelResponse(
+ id="chatcmpl-test",
+ model="openai/strong",
+ choices=[
+ Choices(
+ message=Message(content=None, tool_calls=None),
+ finish_reason="content_filter",
+ )
+ ],
+ usage=Usage(prompt_tokens=0, completion_tokens=0, total_tokens=0),
+ )
+ result = _response(response)
+ outputs = result["outputs"]
+ assert isinstance(outputs, list)
+ output = outputs[0]
+ assert isinstance(output, dict)
+ assert output["content"] == []
+ assert output["stop_reason"] == "content_filter"
+
+
+def test_response_empty_content_without_content_filter_raises() -> None:
+ """Empty content with any other finish reason must still raise."""
+ from switchyard_litellm.client import _response
+
+ response = ModelResponse(
+ id="chatcmpl-test",
+ model="openai/strong",
+ choices=[
+ Choices(
+ message=Message(content=None, tool_calls=None),
+ finish_reason="stop",
+ )
+ ],
+ usage=Usage(prompt_tokens=0, completion_tokens=0, total_tokens=0),
+ )
+ with pytest.raises(ValueError, match="LiteLLM returned no text content"):
+ _response(response)