fix(openai): add reask fallback when RESPONSES_TOOLS output has no tool calls

CHANGELOG.md

@@ -10,6 +10,7 @@ Versioning: [Semantic Versioning](https://semver.org/spec/v2.0.0.html)
 ## [Unreleased]
 
 ### Fixed
+- **OpenAI Responses reask**: Add a fallback correction message when a `RESPONSES_TOOLS` response contains no tool calls (e.g. reasoning-only output), so retries carry validation feedback instead of resending the identical request.
 - **Credential redaction**: Hide common OAuth and Google API credential aliases in nested v2 debug logging while preserving non-secret token configuration. ([#2490](https://github.com/567-labs/instructor/issues/2490), [#2491](https://github.com/567-labs/instructor/pull/2491))
 - **Retry and message integrity**: Preserve cache keys and caller-owned retry messages, retain empty-content legacy function calls, return Anthropic tool results for every parallel tool call, and handle missing OpenAI/Mistral tool calls as retryable parse failures. ([#2454](https://github.com/567-labs/instructor/issues/2454), [#2455](https://github.com/567-labs/instructor/pull/2455), [#2464](https://github.com/567-labs/instructor/issues/2464), [#2484](https://github.com/567-labs/instructor/pull/2484), [#2485](https://github.com/567-labs/instructor/issues/2485), [#2486](https://github.com/567-labs/instructor/pull/2486), [#2448](https://github.com/567-labs/instructor/pull/2448), [#2453](https://github.com/567-labs/instructor/pull/2453))
 - **Streaming and DSL correctness**: Isolate partial-model recursion guards, preserve partial nested models and explicit nulls, harden citation matching, derive useful Iterable union names, and continue scanning JSON streams after non-JSON or multiple balanced values. ([#2422](https://github.com/567-labs/instructor/issues/2422), [#2430](https://github.com/567-labs/instructor/pull/2430), [#2431](https://github.com/567-labs/instructor/issues/2431), [#2452](https://github.com/567-labs/instructor/pull/2452), [#2456](https://github.com/567-labs/instructor/pull/2456), [#2461](https://github.com/567-labs/instructor/issues/2461), [#2463](https://github.com/567-labs/instructor/pull/2463), [#2476](https://github.com/567-labs/instructor/pull/2476), [#2487](https://github.com/567-labs/instructor/pull/2487), [#2489](https://github.com/567-labs/instructor/pull/2489))

instructor/v2/providers/openai/handlers.py

@@ -260,6 +260,21 @@ def reask_responses_tools(
             }
         )
 
+    if not reask_messages:
+        # Model produced no tool calls at all (e.g. a reasoning-only or plain
+        # message output). Fall back to a plain user correction so the retry
+        # carries feedback instead of resending the identical request,
+        # mirroring reask_tools and the Anthropic reask handler.
+        reask_messages.append(
+            {
+                "role": "user",
+                "content": (
+                    f"Validation Error found:\n{exception}\n"
+                    "Recall the function correctly, fix the errors"
+                ),
+            }
+        )
+
     kwargs["messages"].extend(reask_messages)
     return kwargs
 

tests/test_openai_responses_tools.py

@@ -141,6 +141,38 @@ def test_reask_responses_tools_none_arguments() -> None:
     assert "MUST populate ALL required fields" in msg
 
 
+def test_reask_responses_tools_no_tool_calls_adds_fallback_message() -> None:
+    """Reask must add corrective feedback even when the output has no tool calls.
+
+    Reasoning models can return only reasoning/message items instead of the
+    forced function call. Without a fallback the retry resends the identical
+    request with no feedback at all.
+    """
+    reasoning_item = MagicMock()
+    reasoning_item.type = "reasoning"
+
+    message_item = MagicMock()
+    message_item.type = "message"
+
+    response = MagicMock()
+    response.output = [reasoning_item, message_item]
+
+    error = ValueError(
+        "1 validation error for ResponseToolModel\nname\n  Field required"
+    )
+
+    result = reask_responses_tools(
+        {"messages": [{"role": "user", "content": "extract"}]}, response, error
+    )
+
+    assert len(result["messages"]) == 2
+    fallback = result["messages"][-1]
+    assert fallback["role"] == "user"
+    assert "Validation Error found" in fallback["content"]
+    assert "Field required" in fallback["content"]
+    assert "Recall the function correctly" in fallback["content"]
+
+
 def test_responses_tools_overrides_text_type_format() -> None:
     _, kwargs = OpenAIResponsesToolsHandler().prepare_request(
         ResponseToolModel,