[fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4177)

* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix

fastdeploy/entrypoints/engine_client.py

@@ -255,8 +255,13 @@ class EngineClient:
                 raise ValueError(f"max_tokens can be defined [1, {self.max_model_len}).")
 
         if data.get("reasoning_max_tokens") is not None:
-            if data["reasoning_max_tokens"] > data["max_tokens"] or data["reasoning_max_tokens"] < 1:
-                raise ValueError("reasoning_max_tokens must be between max_tokens and 1")
+            if data["reasoning_max_tokens"] < 1:
+                raise ValueError("reasoning_max_tokens must be greater than 1")
+            if data["reasoning_max_tokens"] > data["max_tokens"]:
+                data["reasoning_max_tokens"] = data["max_tokens"]
+                api_server_logger.warning(
+                    f"req_id: {data['request_id']}, reasoning_max_tokens exceeds max_tokens, the value of reasoning_max_tokens will be adjusted to match that of max_tokens"
+                )
 
         if data.get("top_p") is not None:
             if data["top_p"] > 1 or data["top_p"] < 0:

fastdeploy/entrypoints/openai/protocol.py

@@ -588,6 +588,7 @@ class ChatCompletionRequest(BaseModel):
     prompt_token_ids: Optional[List[int]] = None
     max_streaming_response_tokens: Optional[int] = None
     disable_chat_template: Optional[bool] = False
+    completion_token_ids: Optional[List[int]] = None
     # doc: end-chat-completion-extra-params
 
     def to_dict_for_infer(self, request_id=None):
@@ -613,6 +614,9 @@ class ChatCompletionRequest(BaseModel):
             ), "The parameter `raw_request` is not supported now, please use completion api instead."
             for key, value in self.metadata.items():
                 req_dict[key] = value
+            from fastdeploy.utils import api_server_logger
+
+            api_server_logger.warning("The parameter metadata is obsolete.")
         for key, value in self.dict().items():
             if value is not None:
                 req_dict[key] = value