feat: preserve Responses reasoning state and compact context (#5172)

tests/providers/test_litellm_kwargs.py

@@ -14,6 +14,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from nanobot.providers.base import ProviderCallContext
 from nanobot.providers.openai_compat_provider import OpenAICompatProvider
 from nanobot.providers.registry import find_by_name
 
@@ -679,6 +680,7 @@ async def test_direct_openai_gpt5_uses_responses_api() -> None:
     assert call_kwargs["max_output_tokens"] == 4096
     assert "input" in call_kwargs
     assert "messages" not in call_kwargs
+    assert call_kwargs["include"] == ["reasoning.encrypted_content"]
 
 
 @pytest.mark.asyncio
@@ -710,6 +712,40 @@ async def test_direct_openai_reasoning_prefers_responses_api() -> None:
     assert call_kwargs["include"] == ["reasoning.encrypted_content"]
 
 
+@pytest.mark.asyncio
+async def test_direct_openai_retries_without_unsupported_server_compaction() -> None:
+    mock_chat = AsyncMock(return_value=_fake_chat_response())
+    mock_responses = AsyncMock(side_effect=[
+        _FakeResponsesError(400, "Unknown parameter: context_management"),
+        _fake_responses_response("compaction fallback"),
+    ])
+    spec = find_by_name("openai")
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI") as mock_client_class:
+        client_instance = mock_client_class.return_value
+        client_instance.chat.completions.create = mock_chat
+        client_instance.responses.create = mock_responses
+        provider = OpenAICompatProvider(
+            api_key="sk-test-key",
+            default_model="gpt-5.6",
+            spec=spec,
+        )
+
+        result = await provider.chat_with_context(
+            messages=[{"role": "user", "content": "hello"}],
+            model="gpt-5.6",
+            provider_context=ProviderCallContext(context_window_tokens=200_000),
+        )
+
+    assert result.content == "compaction fallback"
+    assert result.provider_state is not None
+    assert mock_responses.await_count == 2
+    assert "context_management" in mock_responses.call_args_list[0].kwargs
+    assert "context_management" not in mock_responses.call_args_list[1].kwargs
+    assert provider.supports_native_compaction("gpt-5.6") is False
+    mock_chat.assert_not_awaited()
+
+
 @pytest.mark.asyncio
 async def test_direct_openai_gpt4o_stays_on_chat_completions() -> None:
     mock_chat = AsyncMock(return_value=_fake_chat_response())