fix(providers): report Responses cached tokens

nanobot/providers/openai_responses/parsing.py

@@ -203,11 +203,16 @@ def _usage_from_response_obj(response: object) -> dict[str, int]:
         usage.get("output_tokens") or usage.get("completion_tokens") or 0
     )
     total_tokens = int(usage.get("total_tokens") or prompt_tokens + completion_tokens)
-    return {
+    result = {
         "prompt_tokens": prompt_tokens,
         "completion_tokens": completion_tokens,
         "total_tokens": total_tokens,
     }
+    input_details = _response_object(usage.get("input_tokens_details"))
+    cached_tokens = int(input_details.get("cached_tokens") or 0) if input_details else 0
+    if cached_tokens > 0:
+        result["cached_tokens"] = cached_tokens
+    return result
 
 
 def _parse_tool_call_arguments(args_raw: Any, name: str | None) -> Any:
@@ -789,6 +794,13 @@ async def consume_sdk_stream(
                         "completion_tokens": int(getattr(usage_obj, "output_tokens", 0) or 0),
                         "total_tokens": int(getattr(usage_obj, "total_tokens", 0) or 0),
                     }
+                    usage_data = _response_object(usage_obj) or {}
+                    input_details = _response_object(usage_data.get("input_tokens_details"))
+                    cached_tokens = (
+                        int(input_details.get("cached_tokens") or 0) if input_details else 0
+                    )
+                    if cached_tokens > 0:
+                        usage["cached_tokens"] = cached_tokens
                 if not reasoning_content:
                     reasoning_content = _extract_reasoning_summary_from_output(
                         getattr(resp, "output", None)

tests/providers/test_openai_responses.py

@@ -1278,14 +1278,24 @@ class TestConsumeSse:
                 "type": "response.completed",
                 "response": {
                     "status": "completed",
-                    "usage": {"input_tokens": 10, "output_tokens": 5, "total_tokens": 15},
+                    "usage": {
+                        "input_tokens": 10,
+                        "input_tokens_details": {"cached_tokens": 8},
+                        "output_tokens": 5,
+                        "total_tokens": 15,
+                    },
                 },
             },
         ])
 
         _, _, _, usage, _ = await consume_sse_with_reasoning(response)
 
-        assert usage == {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}
+        assert usage == {
+            "prompt_tokens": 10,
+            "completion_tokens": 5,
+            "total_tokens": 15,
+            "cached_tokens": 8,
+        }
 
     @pytest.mark.asyncio
     async def test_tool_call_done_arguments_callback(self):
@@ -1752,7 +1762,12 @@ class TestConsumeSdkStream:
 
     @pytest.mark.asyncio
     async def test_usage_extracted(self):
-        usage_obj = MagicMock(input_tokens=10, output_tokens=5, total_tokens=15)
+        usage_obj = MagicMock(
+            input_tokens=10,
+            input_tokens_details=MagicMock(cached_tokens=8),
+            output_tokens=5,
+            total_tokens=15,
+        )
         resp_obj = MagicMock(status="completed", usage=usage_obj, output=[])
         ev = MagicMock(type="response.completed", response=resp_obj)
 
@@ -1760,7 +1775,12 @@ class TestConsumeSdkStream:
             yield ev
 
         _, _, _, usage, _ = await consume_sdk_stream(stream())
-        assert usage == {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}
+        assert usage == {
+            "prompt_tokens": 10,
+            "completion_tokens": 5,
+            "total_tokens": 15,
+            "cached_tokens": 8,
+        }
 
     @pytest.mark.asyncio
     @pytest.mark.parametrize(