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

tests/providers/test_azure_openai_provider.py

@@ -11,7 +11,7 @@ from nanobot.providers.azure_openai_provider import (
     AzureOpenAIProvider,
     _AzureTokenProvider,
 )
-from nanobot.providers.base import LLMResponse
+from nanobot.providers.base import LLMResponse, ProviderCallContext
 
 # ---------------------------------------------------------------------------
 # Init & validation
@@ -234,6 +234,7 @@ def test_build_body_basic():
     assert body["max_output_tokens"] == 4096
     assert body["store"] is False
     assert "reasoning" not in body
+    assert "include" not in body
     # input should contain the converted user message only (system extracted)
     assert any(
         item.get("role") == "user"
@@ -241,6 +242,30 @@ def test_build_body_basic():
     )
 
 
+def test_build_body_enables_server_compaction():
+    provider = AzureOpenAIProvider(
+        api_key="k",
+        api_base="https://res.openai.azure.com",
+        default_model="gpt-5.6",
+    )
+
+    body = provider._build_body(
+        [{"role": "user", "content": "hello"}],
+        None,
+        None,
+        10_000,
+        0.1,
+        "high",
+        None,
+        provider_context=ProviderCallContext(context_window_tokens=200_000),
+    )
+
+    assert body["context_management"] == [{
+        "type": "compaction",
+        "compact_threshold": 180_000,
+    }]
+
+
 def test_build_body_max_tokens_minimum():
     """max_output_tokens should never be less than 1."""
     provider = AzureOpenAIProvider(api_key="k", api_base="https://r.com", default_model="gpt-4o")
@@ -358,6 +383,38 @@ async def test_chat_success():
     assert result.usage["prompt_tokens"] == 10
 
 
+@pytest.mark.asyncio
+async def test_chat_retries_without_unsupported_server_compaction():
+    provider = AzureOpenAIProvider(
+        api_key="test-key",
+        api_base="https://test.openai.azure.com",
+        default_model="gpt-5.6",
+    )
+
+    class UnsupportedCompactionError(Exception):
+        status_code = 400
+        body = {"error": {"message": "Unknown parameter: context_management"}}
+
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(side_effect=[
+        UnsupportedCompactionError(),
+        _make_sdk_response(content="compaction fallback"),
+    ])
+
+    result = await provider.chat(
+        [{"role": "user", "content": "Hi"}],
+        provider_context=ProviderCallContext(context_window_tokens=200_000),
+    )
+
+    create = provider._client.responses.create
+    assert result.content == "compaction fallback"
+    assert result.provider_state is not None
+    assert create.await_count == 2
+    assert "context_management" in create.call_args_list[0].kwargs
+    assert "context_management" not in create.call_args_list[1].kwargs
+    assert provider.supports_native_compaction() is False
+
+
 @pytest.mark.asyncio
 async def test_chat_uses_default_model():
     provider = AzureOpenAIProvider(
@@ -411,6 +468,7 @@ async def test_chat_with_tool_calls():
     assert len(result.tool_calls) == 1
     assert result.tool_calls[0].name == "get_weather"
     assert result.tool_calls[0].arguments == {"location": "SF"}
+    assert result.provider_state is not None
 
 
 @pytest.mark.asyncio
@@ -510,6 +568,7 @@ async def test_chat_stream_with_tool_calls():
     item_done.name = "get_weather"
     ev_item_done = MagicMock(type="response.output_item.done", item=item_done)
     resp_obj = MagicMock(status="completed")
+    resp_obj.model_dump.return_value = {"status": "completed", "output": []}
     ev_completed = MagicMock(type="response.completed", response=resp_obj)
 
     async def mock_stream():
@@ -527,6 +586,7 @@ async def test_chat_stream_with_tool_calls():
     assert len(result.tool_calls) == 1
     assert result.tool_calls[0].name == "get_weather"
     assert result.tool_calls[0].arguments == {"location": "SF"}
+    assert result.provider_state is not None
 
 
 @pytest.mark.asyncio