fix(bedrock): answer a buffered invoke stream from the non-streaming reply

litellm/llms/custom_httpx/llm_http_handler.py

@@ -1056,7 +1056,7 @@ class BaseLLMHTTPHandler:
                 provider_config=provider_config,
                 fake_stream=fake_stream,
             )
-            if provider_config.has_custom_stream_wrapper is True:
+            if provider_config.has_custom_stream_wrapper is True and not fake_stream:
                 return provider_config.get_sync_custom_stream_wrapper(
                     model=model,
                     custom_llm_provider=custom_llm_provider,
@@ -1225,7 +1225,7 @@ class BaseLLMHTTPHandler:
         json_mode: bool | None = None,
         signed_json_body: bytes | None = None,
     ):
-        if provider_config.has_custom_stream_wrapper is True:
+        if provider_config.has_custom_stream_wrapper is True and not fake_stream:
             return await provider_config.get_async_custom_stream_wrapper(
                 model=model,
                 custom_llm_provider=custom_llm_provider,

tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py

@@ -640,6 +640,50 @@ async def test_a_denied_native_output_stream_is_sent_again_buffered_with_native_
     assert "textFormat" in retry_body.get("outputConfig", {}) and "toolConfig" not in retry_body
 
 
+_INVOKE_ANSWER: Final = json.dumps(
+    {
+        "id": "msg_1",
+        "type": "message",
+        "role": "assistant",
+        "model": "claude-opus-5-5",
+        "content": [{"type": "text", "text": '{"answer": "hi"}'}],
+        "stop_reason": "end_turn",
+        "stop_sequence": None,
+        "usage": {"input_tokens": 10, "output_tokens": 5},
+    }
+).encode()
+
+
+def _denies_invoke_streaming_then_answers(request: httpx.Request) -> httpx.Response:
+    if request.url.path.endswith("/invoke-with-response-stream"):
+        return httpx.Response(403, content=_STREAM_PERMISSION_DENIAL, request=request)
+    return httpx.Response(200, content=_INVOKE_ANSWER, headers={"content-type": "application/json"}, request=request)
+
+
+@pytest.mark.asyncio
+async def test_a_denied_native_output_stream_on_the_invoke_route_is_sent_again_buffered_to_invoke(
+    respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
+    respx_mock.post(url__regex=_BEDROCK_RUNTIME_URL).mock(side_effect=_denies_invoke_streaming_then_answers)
+    router: Final = _bedrock_router(
+        "bedrock/invoke/us.anthropic.claude-opus-5-5", timeout=60, stream_timeout=STREAM_TIMEOUT_SECONDS
+    )
+
+    response: Final = await router.acompletion(
+        model="bedrock",
+        messages=[{"role": "user", "content": "hi"}],
+        stream=True,
+        thinking={"type": "disabled"},
+        response_format={"type": "json_schema", "json_schema": {"name": "answer", "schema": _ANSWER_SCHEMA}},
+    )
+
+    assert "".join([chunk.choices[0].delta.content or "" async for chunk in response]) == '{"answer": "hi"}'
+    assert _sent_paths(respx_mock) == ["invoke-with-response-stream", "invoke"]
+    retry_body: Final = json.loads(respx_mock.calls[1].request.content)
+    assert "format" in retry_body.get("output_config", {}) and "tools" not in retry_body
+
+
 @pytest.mark.asyncio
 async def test_failed_native_output_retry_reports_the_request_timeout_it_was_bounded_by(
     respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch

tests/unit/llms/custom_httpx/test_llm_http_handler.py

@@ -4894,6 +4894,10 @@ class _StreamRouteConfig(_TransformRecordingConfig):
     def __init__(self):
         super().__init__(transform_async=False)
 
+    @property
+    def has_custom_stream_wrapper(self) -> bool:
+        return True
+
     def get_complete_url(self, api_base, api_key, model, optional_params, litellm_params, stream=None):
         return f"{api_base}/{'stream' if stream else 'answer'}"