diff --git a/astrbot/core/config/default.py b/astrbot/core/config/default.py
index 85e753a33..44ee238df 100644
--- a/astrbot/core/config/default.py
+++ b/astrbot/core/config/default.py
@@ -29,7 +29,6 @@ DEFAULT_CONFIG = {
             "enable": False,
             "only_llm_result": True,
             "interval": "1.5,3.5",
-            "seg_prompt": "",
             "regex": ".*?[。？！~…]+|.+$"
         },
         "no_permission_reply": True,
@@ -219,11 +218,6 @@ CONFIG_METADATA_2 = {
                                 "type": "string",
                                 "hint": "每一段回复的间隔时间，格式为 `最小时间,最大时间`。如 `0.75,2.5`",
                             },
-                            "seg_prompt": {
-                                "description": "分段提示词辅助",
-                                "type": "string",
-                                "hint": "此项为空时表达不启用这个方法。此方法会调用一次LLM请求。让 LLM 在某一句话中插入一个可以用正则表达式分隔的标记，来实现LLM基于情感分段。如: `请基于情感对以下文本进行分段, 并在两段之间添加`<seg>`以便我用正则匹配。`    然后将下面的正则表达式更换为`.+?<seg>`。",
-                            },
                             "regex": {
                                 "description": "正则表达式",
                                 "type": "string",
diff --git a/astrbot/core/pipeline/result_decorate/stage.py b/astrbot/core/pipeline/result_decorate/stage.py
index c05d4b0bc..b44dc7ea9 100644
--- a/astrbot/core/pipeline/result_decorate/stage.py
+++ b/astrbot/core/pipeline/result_decorate/stage.py
@@ -30,7 +30,6 @@ class ResultDecorateStage:
         # 分段回复
         self.enable_segmented_reply = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
         self.only_llm_result = ctx.astrbot_config['platform_settings']['segmented_reply']['only_llm_result']
-        self.seg_prompt = ctx.astrbot_config['platform_settings']['segmented_reply']['seg_prompt']
         self.regex = ctx.astrbot_config['platform_settings']['segmented_reply']['regex']
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
@@ -57,19 +56,6 @@ class ResultDecorateStage:
                     new_chain = []
                     for comp in result.chain:
                         if isinstance(comp, Plain):
-                            
-                            if self.seg_prompt:
-                                try:
-                                    llm_resp = await self.ctx.plugin_manager.context.get_using_provider().text_chat(
-                                        prompt=f"{self.seg_prompt}\n{comp.text}",
-                                    )
-                                    comp.text = llm_resp.completion_text
-                                except BaseException as e:
-                                    traceback.print_exc()
-                                    logger.warning("使用 LLM 分段回复失败。将不分段回复。： " + str(e))
-                                    new_chain.append(comp)
-                                    continue
-                            
                             split_response = re.findall(self.regex, comp.text)
                             if not split_response:
                                 new_chain.append(comp)