Skip to content

Agent Zero AI framework

Tighten Responses bad request fallback

Alessandro5c914bc49ebd
diff --git a/helpers/litellm_transport.py b/helpers/litellm_transport.py
index 9298ede59..9e7a290f9 100644
--- a/helpers/litellm_transport.py
+++ b/helpers/litellm_transport.py
@@ -1574,10 +1574,9 @@ def _looks_like_responses_request_rejected(text: str) -> bool:
"expected object, received string",
"expected string, received array",
"zod",
- "invalid request",
- "invalid type",
- "failed to deserialize",
- "validation error",
+ "failed to deserialize input",
+ "failed to deserialize response",
+ "failed to deserialize responses",
)
)
diff --git a/helpers/litellm_transport.py.dox.md b/helpers/litellm_transport.py.dox.md
index da8836150..938af1432 100644
--- a/helpers/litellm_transport.py.dox.md
+++ b/helpers/litellm_transport.py.dox.md
@@ -26,7 +26,7 @@
- Strip Agent Zero internal kwargs before sending requests to LiteLLM.
- Do not send orphan tool controls when no tools are present; strict OpenAI-compatible servers can reject empty `tools` arrays.
- Prefer Responses API when configured, but fallback to Chat Completions when the provider does not support Responses.
-- Fall back to Chat Completions when a Responses request is rejected before any output by a Bad Request/validation error that indicates the provider cannot parse the Responses request shape.
+- Fall back to Chat Completions when a Responses request is rejected before any output by an endpoint-specific or shape-specific Bad Request indicating the provider cannot parse Responses payloads.
- Preserve provider-state metadata when Responses API calls succeed, and fall back to local replay when provider state is unsupported.
- Keep prompt-cache markers only for providers that accept them.
diff --git a/tests/test_stream_tool_early_stop.py b/tests/test_stream_tool_early_stop.py
index 791e70e78..a1109948f 100644
--- a/tests/test_stream_tool_early_stop.py
+++ b/tests/test_stream_tool_early_stop.py
@@ -611,6 +611,48 @@ async def test_unified_call_falls_back_when_responses_bad_request_rejects_shape(
assert calls == ["responses", "chat"]
+async def test_unified_call_raises_generic_responses_bad_request(monkeypatch):
+ class BadRequestError(Exception):
+ status_code = 400
+
+ calls: list[str] = []
+
+ async def fake_aresponses(*args, **kwargs):
+ calls.append("responses")
+ raise BadRequestError(
+ "BadRequestError: validation error: invalid request: max_tokens is too high"
+ )
+
+ async def fake_acompletion(*args, **kwargs):
+ calls.append("chat")
+ raise AssertionError("generic 400 should not fallback to chat")
+
+ async def fake_rate_limiter(*args, **kwargs):
+ return None
+
+ monkeypatch.setattr(litellm_transport, "aresponses", fake_aresponses)
+ monkeypatch.setattr(litellm_transport, "acompletion", fake_acompletion)
+ monkeypatch.setattr(models, "apply_rate_limiter", fake_rate_limiter)
+
+ wrapper = models.LiteLLMChatWrapper(
+ model="test-model",
+ provider="openai",
+ model_config=None,
+ )
+
+ async def response_callback(chunk: str, full: str):
+ return None
+
+ with pytest.raises(BadRequestError):
+ await wrapper.unified_call(
+ messages=[],
+ response_callback=response_callback,
+ )
+
+ assert calls == ["responses"]
+
+
@pytest.mark.asyncio
async def test_unified_call_preserves_cache_control_with_chat_for_non_native_responses(
monkeypatch,