Replace --expand-tools-even-if-tool-choice-none with --exclude-tools-when-tool-choice-none for v0.10.0

docs/features/tool_calling.md

@@ -103,7 +103,8 @@ When tool_choice='required' is set, the model is guaranteed to generate one or m
 
 vLLM supports the `tool_choice='none'` option in the chat completion API. When this option is set, the model will not generate any tool calls and will respond with regular text content only, even if tools are defined in the request.
 
-However, when `tool_choice='none'` is specified, vLLM includes tool definitions from the prompt.
+!!! note
+    When tools are specified in the request, vLLM includes tool definitions in the prompt by default, regardless of the `tool_choice` setting. To exclude tool definitions when `tool_choice='none'`, use the `--exclude-tools-when-tool-choice-none` option.
 
 ## Automatic Function Calling
 

vllm/entrypoints/openai/api_server.py

@@ -1647,6 +1647,8 @@ async def init_app_state(
         chat_template_content_format=args.chat_template_content_format,
         return_tokens_as_token_ids=args.return_tokens_as_token_ids,
         enable_auto_tools=args.enable_auto_tool_choice,
+        exclude_tools_when_tool_choice_none=args.
+        exclude_tools_when_tool_choice_none,
         tool_parser=args.tool_call_parser,
         reasoning_parser=args.reasoning_parser,
         enable_prompt_tokens_details=args.enable_prompt_tokens_details,

vllm/entrypoints/openai/cli_args.py

@@ -158,6 +158,9 @@ class FrontendArgs:
     """If specified, API server will add X-Request-Id header to responses. 
     Caution: this hurts performance at high QPS."""
     enable_auto_tool_choice: bool = False
+    """If specified, exclude tool definitions in prompts when 
+    tool_choice='none'."""
+    exclude_tools_when_tool_choice_none: bool = False
     """Enable auto tool choice for supported models. Use `--tool-call-parser` 
     to specify which parser to use."""
     tool_call_parser: Optional[str] = None

vllm/entrypoints/openai/serving_chat.py

@@ -63,6 +63,7 @@ def __init__(
         return_tokens_as_token_ids: bool = False,
         reasoning_parser: str = "",
         enable_auto_tools: bool = False,
+        exclude_tools_when_tool_choice_none: bool = False,
         tool_parser: Optional[str] = None,
         enable_prompt_tokens_details: bool = False,
         enable_force_include_usage: bool = False,
@@ -111,6 +112,8 @@ def __init__(
                 raise TypeError("Error: --enable-auto-tool-choice requires "
                                 f"tool_parser:'{tool_parser}' which has not "
                                 "been registered") from e
+        self.exclude_tools_when_tool_choice_none = (
+            exclude_tools_when_tool_choice_none)
 
         self.enable_prompt_tokens_details = enable_prompt_tokens_details
         self.enable_force_include_usage = enable_force_include_usage
@@ -177,7 +180,9 @@ async def create_chat_completion(
                     "--enable-auto-tool-choice and --tool-call-parser to be set"
                 )
 
-            if request.tools is None:
+            if (request.tools is None
+                    or (request.tool_choice == "none"
+                        and self.exclude_tools_when_tool_choice_none)):
                 tool_dicts = None
             else:
                 tool_dicts = [tool.model_dump() for tool in request.tools]