test(llm): cover reasoning effort overrides

config/llm_config.yaml

@@ -7,6 +7,8 @@ llm:
 
   temperature: 1
   max_tokens: 32768
+  # reasoning_effort: "high"  # optional; use a provider-supported level
+                              # such as low, medium, or high
   routing: {}
   fallback: {}
 

tests/test_llm_provider_reasoning_effort.py

@@ -64,6 +64,26 @@ class TestLLMProviderReasoningEffort(unittest.IsolatedAsyncioTestCase):
 
         assert completion.await_args.kwargs["reasoning_effort"] == "max"
 
+    async def test_chat_allows_per_call_reasoning_effort_override(self) -> None:
+        provider = LLMProvider(LLMConfig(
+            default_model="openai/gpt-5.6-luna",
+            reasoning_effort="high",
+        ))
+
+        with (
+            patch("opc.llm.provider._clamp_max_tokens", return_value=128),
+            patch(
+                "opc.llm.provider.litellm.acompletion",
+                new=AsyncMock(return_value=_completion_response()),
+            ) as completion,
+        ):
+            await provider.chat(
+                [{"role": "user", "content": "hello"}],
+                reasoning_effort="low",
+            )
+
+        assert completion.await_args.kwargs["reasoning_effort"] == "low"
+
     async def test_chat_stream_forwards_configured_reasoning_effort(self) -> None:
         provider = LLMProvider(LLMConfig(
             default_model="openai/gpt-5.6-luna",
@@ -88,6 +108,30 @@ class TestLLMProviderReasoningEffort(unittest.IsolatedAsyncioTestCase):
         assert completion.await_args.kwargs["reasoning_effort"] == "max"
         assert completion.await_args.kwargs["stream"] is True
 
+    async def test_chat_stream_allows_per_call_reasoning_effort_override(self) -> None:
+        provider = LLMProvider(LLMConfig(
+            default_model="openai/gpt-5.6-luna",
+            reasoning_effort="high",
+        ))
+
+        with (
+            patch("opc.llm.provider._clamp_max_tokens", return_value=128),
+            patch(
+                "opc.llm.provider.litellm.acompletion",
+                new=AsyncMock(return_value=_completion_stream()),
+            ) as completion,
+        ):
+            events = [
+                event
+                async for event in provider.chat_stream(
+                    [{"role": "user", "content": "hello"}],
+                    reasoning_effort="low",
+                )
+            ]
+
+        assert events
+        assert completion.await_args.kwargs["reasoning_effort"] == "low"
+
     async def test_unset_reasoning_effort_is_not_added_to_requests(self) -> None:
         provider = LLMProvider(LLMConfig(default_model="openai/gpt-5.6-luna"))