fix(responses): emit the reasoning item on streaming /v1/responses for signature-only thinking

Anthropic models return thinking blocks with empty text and the reasoning carried in the
signature: Claude Fable 5.1 and Claude Opus 5.5 by default, and Bedrock adaptive thinking
with or without an effort. On streaming /v1/responses the chat->Responses bridge opened a
reasoning output item only on reasoning_content text
(LiteLLMCompletionStreamingIterator._ensure_output_item_for_chunk), and
ChunkProcessor.get_combined_thinking_content kept an assembled thinking block only when it
had thinking text. Such a response emitted no reasoning item mid-stream and none in
response.completed, so a streaming Responses client could not replay the reasoning even
though the reasoning tokens were billed. Non-streaming /v1/responses was unaffected.

Open the reasoning item when the delta carries a signed or redacted thinking block, and
keep a signed block through stream assembly even when its thinking text is empty.
Unsigned text-only fragments are still dropped. The reasoning-text path is unchanged.

litellm/litellm_core_utils/streaming_chunk_builder_utils.py

@@ -685,7 +685,7 @@ class ChunkProcessor:
 
         def _flush_thinking_block() -> None:
             nonlocal current_thinking_text_parts, current_signature
-            if len(current_thinking_text_parts) > 0 and current_signature:
+            if current_signature:
                 thinking_blocks.append(
                     ChatCompletionThinkingBlock(
                         type="thinking",

litellm/responses/litellm_completion_transformation/streaming_iterator.py

@@ -73,6 +73,11 @@ def _output_items_with_id(items: tuple[Any, ...], item_type: str, item_id: str |
     )
 
 
+def _delta_has_signed_thinking_block(delta: object) -> bool:
+    blocks: Final = getattr(delta, "thinking_blocks", None) or ()
+    return any(isinstance(b, dict) and (b.get("signature") or b.get("data")) for b in blocks)
+
+
 class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
     """
     Async iterator for processing streaming responses from the Responses API.
@@ -936,7 +941,7 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator):
         self.sent_output_item_added_event = True
 
         # Reasoning-first
-        if hasattr(delta, "reasoning_content") and delta.reasoning_content:
+        if (hasattr(delta, "reasoning_content") and delta.reasoning_content) or _delta_has_signed_thinking_block(delta):
             self._reasoning_active = True
             if self._cached_reasoning_item_id is None:
                 self._cached_reasoning_item_id = f"rs_{uuid.uuid4()}"

tests/test_litellm/litellm_core_utils/test_streaming_chunk_builder_utils.py

@@ -236,6 +236,31 @@ def test_get_combined_thinking_content_preserves_interleaved_blocks():
     assert result[2]["signature"] == "sig_block2"
 
 
+def test_get_combined_thinking_content_keeps_signed_block_without_thinking_text():
+    chunks: Final = [
+        ModelResponseStream(
+            id="chatcmpl-123",
+            object="chat.completion.chunk",
+            created=1234567890,
+            model="claude-sonnet-4-20250514",
+            choices=[
+                StreamingChoices(
+                    index=0,
+                    delta=Delta(thinking_blocks=[{"type": "thinking", "thinking": "", "signature": "sig_only"}]),
+                    finish_reason=None,
+                )
+            ],
+        )
+    ]
+
+    result: Final = ChunkProcessor(chunks=chunks).get_combined_thinking_content(chunks)
+
+    assert result is not None
+    assert [(block["type"], block["thinking"], block["signature"]) for block in result] == [
+        ("thinking", "", "sig_only")
+    ]
+
+
 def test_cache_read_input_tokens_retained():
     chunk1 = ModelResponseStream(
         id="chatcmpl-95aabb85-c39f-443d-ae96-0370c404d70c",

tests/test_litellm/responses/litellm_completion_transformation/test_streaming_iterator_transformation.py

@@ -978,6 +978,25 @@ def _reasoning_chunk(reasoning: str, finish_reason: str | None = None) -> ModelR
     )
 
 
+def _signature_only_thinking_chunk(signature: str) -> ModelResponseStream:
+    return ModelResponseStream(
+        id=CHAT_COMPLETION_ID,
+        created=1748575031,
+        model="claude-haiku-4-5",
+        object="chat.completion.chunk",
+        choices=[
+            StreamingChoices(
+                index=0,
+                delta=Delta(
+                    role="assistant",
+                    thinking_blocks=[{"type": "thinking", "thinking": "", "signature": signature}],
+                ),
+                finish_reason=None,
+            )
+        ],
+    )
+
+
 async def _collect_events(
     iterator: LiteLLMCompletionStreamingIterator, sync_mode: bool
 ) -> list[BaseLiteLLMOpenAIResponseObject]:
@@ -1015,6 +1034,27 @@ async def test_tool_only_stream_emits_no_message_item_events(sync_mode: bool):
     assert any(getattr(event, "type", None) == ResponsesAPIStreamEvents.RESPONSE_COMPLETED for event in events)
 
 
+@pytest.mark.parametrize("sync_mode", [True, False])
+@pytest.mark.asyncio
+async def test_signature_only_thinking_streams_a_replayable_reasoning_item(sync_mode: bool):
+    iterator: Final = _build_iterator([_signature_only_thinking_chunk("sig_only"), _chunk("4", finish_reason="stop")])
+
+    events: Final = await _collect_events(iterator, sync_mode)
+
+    added_item_types: Final = [
+        event.item.type
+        for event in events
+        if getattr(event, "type", None) == ResponsesAPIStreamEvents.OUTPUT_ITEM_ADDED
+    ]
+    completed: Final = next(
+        event for event in events if getattr(event, "type", None) == ResponsesAPIStreamEvents.RESPONSE_COMPLETED
+    )
+    reasoning_items: Final = [item for item in completed.response.output if getattr(item, "type", None) == "reasoning"]
+    assert added_item_types[0] == "reasoning"
+    assert len(reasoning_items) == 1
+    assert json.loads(reasoning_items[0].encrypted_content)[0]["signature"] == "sig_only"
+
+
 @pytest.mark.parametrize("sync_mode", [True, False])
 @pytest.mark.asyncio
 async def test_reasoning_then_text_announces_message_item_before_text_events(sync_mode: bool):