responses feedback items: whitelist input-shape fields — api rejects response-only fields like status as unknown parameters (live 400)

fjerkroa_bot/openai_responder.py

@@ -304,6 +304,31 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
                 items.append({"role": role, "content": str(content)})
         return items
 
+    # Only these item types travel back as input; response-only fields like `status`
+    # are rejected by the API as unknown parameters (live 400, 2026-07-17)
+    _RESPONSES_FEEDBACK_FIELDS = {
+        "reasoning": ("id", "summary", "encrypted_content"),
+        "function_call": ("id", "call_id", "name", "arguments"),
+    }
+
+    @classmethod
+    def _responses_feedback(cls, output: List[Any]) -> List[Dict[str, Any]]:
+        """Reasoning + function_call items in input shape — keeps the chain of thought (ENV-23)."""
+        items: List[Dict[str, Any]] = []
+        for item in output or []:
+            fields = cls._RESPONSES_FEEDBACK_FIELDS.get(getattr(item, "type", None) or "")
+            if not fields:
+                continue  # message items need not travel back
+            data: Dict[str, Any] = {"type": item.type}
+            for field in fields:
+                value = getattr(item, field, None)
+                if field == "summary" and isinstance(value, list):
+                    value = [part if isinstance(part, dict) else part.model_dump() for part in value]
+                if value is not None:
+                    data[field] = value
+            items.append(data)
+        return items
+
     @staticmethod
     def _responses_refused(result: Any) -> bool:
         for item in getattr(result, "output", []) or []:
@@ -350,8 +375,8 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
                 return answer, limit
             tool_names = [call.name for call in calls]
             logging.info(f"🔧 OpenAI requested function calls: {tool_names}")
-            # Pass ALL output items back — reasoning items keep the chain of thought (ENV-23)
-            context = context + [item if isinstance(item, dict) else item.model_dump() for item in result.output]
+            # Pass reasoning + function_call items back — keeps the chain of thought (ENV-23)
+            context = context + self._responses_feedback(result.output)
             for call in calls:
                 function_args = json.loads(call.arguments) if call.arguments else {}
                 logging.info(f"🔧 Executing tool: {call.name} with args: {function_args}")

specs/SPEC-001-responder-envelope.md

@@ -169,8 +169,10 @@ chat/completions.
 
 The Responses path runs with `store=false` and
 `include=["reasoning.encrypted_content"]` (nothing retained
-server-side). On a function call, ALL output items — including
-reasoning items — are passed back as input together with one
+server-side). On a function call, the reasoning and function_call
+output items are passed back as input — reduced to their input-shape
+fields, since response-only fields like `status` are rejected as
+unknown parameters (live 400, 2026-07-17) — together with one
 `function_call_output` per call (matched by `call_id`, result
 sanitized per SAF-03), so the model continues one chain of thought
 across tool rounds. Up to `responses-tool-rounds` (default 4) rounds

tests/test_spec_responses.py

@@ -40,17 +40,21 @@ def _refusal_item():
 def _reasoning_item():
     item = Mock()
     item.type = "reasoning"
-    item.model_dump = lambda: {"type": "reasoning", "encrypted_content": "opaque-cot"}
+    item.id = "rs_1"
+    item.summary = []
+    item.encrypted_content = "opaque-cot"
+    item.status = "completed"  # response-only field; must NOT travel back
     return item
 
 
 def _call_item(name, args, call_id="call-1"):
     item = Mock()
     item.type = "function_call"
+    item.id = "fc_1"
     item.name = name
     item.arguments = json.dumps(args)
     item.call_id = call_id
-    item.model_dump = lambda: {"type": "function_call", "name": name, "arguments": json.dumps(args), "call_id": call_id}
+    item.status = "completed"
     return item
 
 
@@ -116,7 +120,12 @@ class TestResponsesPath(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(json.loads(answer["content"])["answer"], "done")
         responder._dispatch_tool.assert_awaited_once()
         followup_input = responses_mock.await_args_list[1].kwargs["input"]
-        self.assertIn({"type": "reasoning", "encrypted_content": "opaque-cot"}, followup_input)
+        reasoning = [item for item in followup_input if isinstance(item, dict) and item.get("type") == "reasoning"]
+        self.assertEqual(len(reasoning), 1)
+        self.assertEqual(reasoning[0]["encrypted_content"], "opaque-cot")
+        self.assertNotIn("status", reasoning[0])  # response-only field stripped (live-400 regression)
+        calls_back = [item for item in followup_input if isinstance(item, dict) and item.get("type") == "function_call"]
+        self.assertNotIn("status", calls_back[0])
         outputs = [item for item in followup_input if isinstance(item, dict) and item.get("type") == "function_call_output"]
         self.assertEqual(len(outputs), 1)
         self.assertEqual(outputs[0]["call_id"], "call-9")