[BugFix] Do not raise a ValueError when tool_choice is set to the supported none option and tools are not defined. (#10000)

Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>

vllm/entrypoints/openai/protocol.py

@@ -454,6 +454,12 @@ class ChatCompletionRequest(OpenAIBaseModel):
         if "tool_choice" not in data and data.get("tools"):
             data["tool_choice"] = "auto"
 
+        # if "tool_choice" is "none" -- ignore tools if present
+        if "tool_choice" in data and data["tool_choice"] == "none":
+            # ensure that no tools are present
+            data.pop("tools", None)
+            return data
+
         # if "tool_choice" is specified -- validation
         if "tool_choice" in data:
 
@@ -467,8 +473,8 @@ class ChatCompletionRequest(OpenAIBaseModel):
             if data["tool_choice"] != "auto" and not isinstance(
                     data["tool_choice"], dict):
                 raise ValueError(
-                    "`tool_choice` must either be a named tool or \"auto\". "
-                    "`tool_choice=\"none\" is not supported.")
+                    "`tool_choice` must either be a named tool, \"auto\", "
+                    "or \"none\".")
 
             # ensure that if "tool_choice" is specified as an object,
             # it matches a valid tool

vllm/entrypoints/openai/serving_engine.py

@@ -469,12 +469,19 @@ class OpenAIServing:
 
         mm_data = await mm_data_future
 
-        if tool_parser is not None:
+        # tool parsing is done only if a tool_parser has been set and if
+        # tool_choice is not "none" (if tool_choice is "none" but a tool_parser
+        # is set, we want to prevent parsing a tool_call hallucinated by the LLM
+        should_parse_tools = tool_parser is not None and (hasattr(
+            request, "tool_choice") and request.tool_choice != "none")
+
+        if should_parse_tools:
             if not isinstance(request, ChatCompletionRequest):
                 msg = "Tool usage is only supported for Chat Completions API"
                 raise NotImplementedError(msg)
 
-            request = tool_parser(tokenizer).adjust_request(request=request)
+            request = tool_parser(tokenizer).adjust_request(  # type: ignore
+                request=request)
 
         if isinstance(request_prompt, str):
             prompt_inputs = self._tokenize_prompt_input(