`reasoning_content` -> `reasoning` (#27752)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/reasoning/minimax_m2_reasoning_parser.py

@@ -48,7 +48,7 @@ class MiniMaxM2AppendThinkReasoningParser(ReasoningParser):
     def extract_content_ids(self, input_ids: list[int]) -> list[int]:
         return input_ids
 
-    def extract_reasoning_content_streaming(
+    def extract_reasoning_streaming(
         self,
         previous_text: str,
         current_text: str,
@@ -61,7 +61,7 @@ class MiniMaxM2AppendThinkReasoningParser(ReasoningParser):
             delta_text = "<think>" + delta_text
         return DeltaMessage(content=delta_text)
 
-    def extract_reasoning_content(
+    def extract_reasoning(
         self, model_output: str, request: ChatCompletionRequest | ResponsesRequest
     ) -> tuple[str | None, str | None]:
         return None, "<think>" + model_output

vllm/reasoning/olmo3_reasoning_parser.py

@@ -115,7 +115,7 @@ class Olmo3ReasoningBuffer:
             if end_think_idx > 0:
                 # this covers the case there's content before
                 # the end of the reasoning block
-                return DeltaMessage(reasoning_content=pretext)
+                return DeltaMessage(reasoning=pretext)
 
         if self.state == Olmo3ReasoningState.REASONING:
             # we are inside reasoning block, return and empty
@@ -124,7 +124,7 @@ class Olmo3ReasoningBuffer:
                 text_buffer,
                 self.buffer,
             ) = self.buffer, ""
-            return DeltaMessage(reasoning_content=text_buffer)
+            return DeltaMessage(reasoning=text_buffer)
 
         if self.state == Olmo3ReasoningState.CONTENT:
             # we are outside reasoning block, return and empty
@@ -250,7 +250,7 @@ class Olmo3ReasoningParser(ReasoningParser):
         # this id is not part of content, so just return [] here.
         return []
 
-    def extract_reasoning_content(
+    def extract_reasoning(
         self,
         model_output: str,
         request: ChatCompletionRequest | ResponsesRequest,
@@ -271,14 +271,14 @@ class Olmo3ReasoningParser(ReasoningParser):
 
         re_match = self.reasoning_regex.match(model_output)
         if re_match:
-            reasoning_content = re_match.group("reasoning") or None
+            reasoning = re_match.group("reasoning") or None
             content = re_match.group("content") or None
-            return reasoning_content, content
+            return reasoning, content
 
         # no reasoning content
         return None, model_output
 
-    def extract_reasoning_content_streaming(
+    def extract_reasoning_streaming(
         self,
         previous_text: str,
         current_text: str,

vllm/reasoning/qwen3_reasoning_parser.py

@@ -27,7 +27,7 @@ class Qwen3ReasoningParser(BaseThinkingReasoningParser):
         """The token that ends reasoning content."""
         return "</think>"
 
-    def extract_reasoning_content(
+    def extract_reasoning(
         self, model_output: str, request: ChatCompletionRequest | ResponsesRequest
     ) -> tuple[str | None, str | None]:
         """
@@ -37,7 +37,7 @@ class Qwen3ReasoningParser(BaseThinkingReasoningParser):
         to be present, unlike other models that work with just the end token.
 
         For text <think>abc</think>xyz:
-        - 'abc' goes to reasoning_content
+        - 'abc' goes to reasoning
         - 'xyz' goes to content
 
         Returns:
@@ -61,7 +61,7 @@ class Qwen3ReasoningParser(BaseThinkingReasoningParser):
             return None, model_output
 
         # Extract reasoning content from the model output.
-        reasoning_content, _, content = model_output.partition(self.end_token)
+        reasoning, _, content = model_output.partition(self.end_token)
 
         final_content = content or None
-        return reasoning_content, final_content
+        return reasoning, final_content

vllm/reasoning/step3_reasoning_parser.py

@@ -40,7 +40,7 @@ class Step3ReasoningParser(ReasoningParser):
                 "token in the tokenizer!"
             )
 
-    def extract_reasoning_content_streaming(
+    def extract_reasoning_streaming(
         self,
         previous_text: str,
         current_text: str,
@@ -54,7 +54,7 @@ class Step3ReasoningParser(ReasoningParser):
         Handles streaming output where previous + delta = current.
         Uses token IDs for faster processing.
         For text "abc</think>xyz":
-        - 'abc' goes to reasoning_content
+        - 'abc' goes to reasoning
         - 'xyz' goes to content
         """
         # Skip single special token
@@ -64,10 +64,10 @@ class Step3ReasoningParser(ReasoningParser):
         if self.think_end_token_id in delta_token_ids:
             # </think> in delta, extract reasoning content and remaining content
             end_index = delta_text.find(self.think_end_token)
-            reasoning_content = delta_text[:end_index]
+            reasoning = delta_text[:end_index]
             content = delta_text[end_index + len(self.think_end_token) :]
             return DeltaMessage(
-                reasoning_content=reasoning_content,
+                reasoning=reasoning,
                 content=content if content else None,
             )
         elif self.think_end_token_id in previous_token_ids:
@@ -75,9 +75,9 @@ class Step3ReasoningParser(ReasoningParser):
             return DeltaMessage(content=delta_text)
         else:
             # No </think> seen yet, everything is reasoning
-            return DeltaMessage(reasoning_content=delta_text)
+            return DeltaMessage(reasoning=delta_text)
 
-    def extract_reasoning_content(
+    def extract_reasoning(
         self, model_output: str, request: ChatCompletionRequest
     ) -> tuple[str | None, str | None]:
         # Check if the model output contains the </think> token
@@ -87,7 +87,7 @@ class Step3ReasoningParser(ReasoningParser):
         else:
             # Find the first occurrence of </think>
             end_index = model_output.find(self.think_end_token)
-            reasoning_content = model_output[:end_index]
+            reasoning = model_output[:end_index]
 
             # Content after </think> token
             content = model_output[end_index + len(self.think_end_token) :]
@@ -95,7 +95,7 @@ class Step3ReasoningParser(ReasoningParser):
             if len(content) == 0:
                 content = None
 
-            return reasoning_content, content
+            return reasoning, content
 
     def is_reasoning_end(self, input_ids: list[int]) -> bool:
         return self.think_end_token_id in input_ids

vllm/transformers_utils/chat_templates/template_minicpmv45.jinja

@@ -30,18 +30,18 @@
         {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
         {%- set content = message.content %}
-        {%- set reasoning_content = '' %}
-        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
-            {%- set reasoning_content = message.reasoning_content %}
+        {%- set reasoning = '' %}
+        {%- if message.reasoning is defined and message.reasoning is not none %}
+            {%- set reasoning = message.reasoning %}
         {%- else %}
             {%- if '</think>' in message.content %}
                 {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
-                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set reasoning = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
-            {%- if loop.last or (not loop.last and reasoning_content) %}
-                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- if loop.last or (not loop.last and reasoning) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
             {%- else %}
                 {{- '<|im_start|>' + message.role + '\n' + content }}
             {%- endif %}

vllm/transformers_utils/tokenizers/mistral.py

@@ -121,8 +121,8 @@ def _prepare_apply_chat_template_tools_and_messages(
     #
     # [1]: https://github.com/mistralai/mistral-common/blob/f4a06998b75ed78bbf5aaf569590b772ea26c9f6/src/mistral_common/protocol/instruct/messages.py#L80
     for message in messages:
-        # Remove reasoning_content as unsupported by Mistral
-        _ = message.pop("reasoning_content", None)  # type: ignore
+        # Remove reasoning as unsupported by Mistral
+        _ = message.pop("reasoning", None)  # type: ignore
 
     # The Mistral client, in comparison to the OpenAI client, requires the
     # "parameters" dict and the "description" string to be present