Merge branch 'py_test_end' into fix-end

main/xiaozhi-server/core/connection.py

@@ -24,7 +24,7 @@ from core.utils.modules_initialize import (
     initialize_tts,
     initialize_asr,
 )
-from core.handle.reportHandle import report
+from core.handle.reportHandle import report, enqueue_tool_report
 from core.providers.tts.default import DefaultTTS
 from concurrent.futures import ThreadPoolExecutor
 from core.utils.dialogue import Message, Dialogue
@@ -46,6 +46,38 @@ from core.utils import textUtils
 
 TAG = __name__
 
+# 工具调用规则 - 用于动态注入提醒
+TOOL_CALLING_RULES = """
+<tool_calling>
+【核心原则】你是拥有工具能力的智能助手。当用户请求需要实时信息或执行操作时，调用相应工具获取数据，禁止凭空编造答案。
+
+- **何时必须调用工具：**
+  1. 实时信息查询（新闻、非本地天气、股价、汇率等）
+  2. 执行操作（播放音乐、控制设备、拍照、设置闹钟等）
+  3. 知识库检索（当工具列表包含 search_from_ragflow 时，结合用户意图判断是否需要调用）
+  4. 查询非今天的农历信息（明天农历、某日宜忌、节气等）
+  5. 用户说"拍照"时调用 self_camera_take_photo，默认 question 参数为"描述一下看到的物品"
+
+- **何时无需调用工具：**
+  1. `<context>` 中已提供的信息（当前时间、今天日期、今天农历、本地天气等）
+  2. 普通对话、问候、闲聊、情感交流、讲故事
+  3. 通用知识问答（非实时信息）
+
+- **调用规范：**
+  1. 每次请求独立判断，不复用历史工具结果，需重新获取最新数据
+  2. 多任务时依次调用所有需要的工具，并依次总结每个工具的结果，不得遗漏
+  3. 严格遵循工具的参数要求，提供所有必要参数
+  4. 不确定时引导用户澄清或告知能力限制，切勿猜测或编造
+  5. 不调用未提供的工具，对话中提及的旧工具若不可用则忽略或说明
+
+- **反偷懒机制（最高优先级）：**
+  1. **每次独立判断：** 无论对话历史中是否调用过工具，当前请求必须根据当前需求独立判断是否需要调用
+  2. **禁止模式模仿：** 即使之前的回复没有调用工具，也不代表本次可以不调用
+  3. **自我检查：** 回复前必须自问："这个请求是否涉及实时信息或执行操作？如果是，我调用工具了吗？"
+  4. **历史不等于现在：** 对话历史中的行为模式不影响当前判断，每个用户请求都是全新的开始
+</tool_calling>
+"""
+
 auto_import_modules("plugins_func.functions")
 
 
@@ -55,14 +87,14 @@ class TTSException(RuntimeError):
 
 class ConnectionHandler:
     def __init__(
-        self,
-        config: Dict[str, Any],
-        _vad,
-        _asr,
-        _llm,
-        _memory,
-        _intent,
-        server=None,
+            self,
+            config: Dict[str, Any],
+            _vad,
+            _asr,
+            _llm,
+            _memory,
+            _intent,
+            server=None,
     ):
         self.common_config = config
         self.config = copy.deepcopy(config)
@@ -140,6 +172,12 @@ class ConnectionHandler:
         # llm相关变量
         self.dialogue = Dialogue()
 
+        # 工具调用统计（用于监控和自动恢复）
+        self.tool_call_stats = {
+            'last_call_turn': -1,  # 上次调用工具的轮数
+            'consecutive_no_call': 0,  # 连续未调用次数
+        }
+
         # tts相关变量
         self.sentence_id = None
         # 处理TTS响应没有文本返回
@@ -157,7 +195,7 @@ class ConnectionHandler:
         self.intent_type = "nointent"
 
         self.timeout_seconds = (
-            int(self.config.get("close_connection_no_voice_time", 120)) + 60
+                int(self.config.get("close_connection_no_voice_time", 120)) + 60
         )  # 在原来第一道关闭的基础上加60秒，进行二道关闭
         self.timeout_task = None
 
@@ -529,9 +567,9 @@ class ConnectionHandler:
     def _initialize_asr(self):
         """初始化ASR"""
         if (
-            self._asr is not None
-            and hasattr(self._asr, "interface_type")
-            and self._asr.interface_type == InterfaceType.LOCAL
+                self._asr is not None
+                and hasattr(self._asr, "interface_type")
+                and self._asr.interface_type == InterfaceType.LOCAL
         ):
             # 如果公共ASR是本地服务，则直接返回
             # 因为本地一个实例ASR，可以被多个连接共享
@@ -719,8 +757,8 @@ class ConnectionHandler:
         memory_type = self.config["Memory"][self.config["selected_module"]["Memory"]][
             "type"
         ]
-        # 如果使用 nomen，直接返回
-        if memory_type == "nomem":
+        # 如果使用 nomen 或 mem_report_only，直接返回
+        if memory_type == "nomem" or memory_type == "mem_report_only":
             return
         # 使用 mem_local_short 模式
         elif memory_type == "mem_local_short":
@@ -832,17 +870,77 @@ class ConnectionHandler:
                 )
             )
 
+        # 长对话工具调用提醒：当对话轮数较多时，提醒模型正确使用工具
+        force_reminder = False  # 是否强制提醒
+
+        if depth == 0 and query is not None:
+            dialogue_length = len(self.dialogue.dialogue)
+            current_turn = dialogue_length // 2
+
+            # 检测距离上一次连续未调用工具的情况
+            if self.tool_call_stats['last_call_turn'] >= 0:
+                turns_since_last = current_turn - self.tool_call_stats['last_call_turn']
+                if turns_since_last > 3:  # 超过3轮未调用
+                    self.logger.bind(tag=TAG).warning(
+                        f"检测到{turns_since_last}轮未调用工具，可能进入偷懒模式，将强制注入提醒"
+                    )
+                    force_reminder = True
+
+            # 对话历史截断：防止历史过长导致模型"偷懒模式"扩散
+            # 当对话历史超过阈值时，保留最近的 10 轮对话
+            # max_dialogue_turns = 10
+            # if dialogue_length > max_dialogue_turns * 2:
+            #     removed = self.dialogue.trim_history(max_turns=max_dialogue_turns)
+            #     if removed > 0:
+            #         self.logger.bind(tag=TAG).info(
+            #             f"对话历史过长({dialogue_length}条)，已智能截断保留最近{max_dialogue_turns}轮，移除{removed}条消息"
+            #         )
+
         # Define intent functions
         functions = None
         # 达到最大深度时，禁用工具调用，强制 LLM 直接回答
         if (
-            self.intent_type == "function_call"
-            and hasattr(self, "func_handler")
-            and not force_final_answer
+                self.intent_type == "function_call"
+                and hasattr(self, "func_handler")
+                and not force_final_answer
         ):
             functions = self.func_handler.get_functions()
+
+        # 长对话工具调用规则强化：动态生成基于当前可用工具的提醒
+        tool_call_reminder = None
+        if depth == 0 and query is not None and functions is not None:
+            dialogue_length = len(self.dialogue.dialogue)
+            # 当对话历史超过4条消息时，注入规则强化
+            if dialogue_length > 4:
+                tool_summary = self._get_tool_summary(functions)
+                if tool_summary:
+                    # 根据对话长度和偷懒检测，使用不同强度的提醒
+                    if force_reminder:
+                        # 强提醒 - 包含完整规则前缀
+                        tool_call_reminder = (
+                            TOOL_CALLING_RULES +
+                            f"[重要提醒] 多轮未使用工具，检查回复是否遗漏了必要的工具调用！上一轮未使用工具，本轮必须重新判断是否需要工具。"
+                            f"当前可用工具: {tool_summary}。"
+                        )
+                        reminder_level = "强"
+                    else:
+                        # 中等提醒 - 包含规则前缀
+                        tool_call_reminder = (
+                            TOOL_CALLING_RULES +
+                            f"当前可用工具: {tool_summary}。"
+                            f"仅当用户请求涉及实时信息查询或执行操作时调用，日常对话无需调用。"
+                        )
+                        reminder_level = "中"
+                    self.logger.bind(tag=TAG).debug(
+                        f"对话历史较长({dialogue_length}条)，已注入{reminder_level}等级工具调用规则强化，当前可用工具：{tool_summary}"
+                    )
+
         response_message = []
 
+        # 如果有工具调用提醒，临时添加到对话中（标记为临时消息）
+        if tool_call_reminder:
+            self.dialogue.put(Message(role="user", content=tool_call_reminder, is_temporary=True))
+
         try:
             # 使用带记忆的对话
             memory_str = None
@@ -971,6 +1069,19 @@ class ConnectionHandler:
                     )
 
             if not bHasError and len(tool_calls_list) > 0:
+                self.logger.bind(tag=TAG).debug(
+                    f"检测到 {len(tool_calls_list)} 个工具调用"
+                )
+
+                # 更新工具调用统计
+                if depth == 0:
+                    current_turn = len(self.dialogue.dialogue) // 2
+                    self.tool_call_stats['last_call_turn'] = current_turn
+                    self.tool_call_stats['consecutive_no_call'] = 0
+                    self.logger.bind(tag=TAG).debug(
+                        f"工具调用统计更新: 当前轮次={current_turn}"
+                    )
+
                 # 如需要大模型先处理一轮，添加相关处理后的日志情况
                 if len(response_message) > 0:
                     text_buff = "".join(response_message)
@@ -978,10 +1089,6 @@ class ConnectionHandler:
                     self.dialogue.put(Message(role="assistant", content=text_buff))
                 response_message.clear()
 
-                self.logger.bind(tag=TAG).debug(
-                    f"检测到 {len(tool_calls_list)} 个工具调用"
-                )
-
                 # 收集所有工具调用的 Future
                 futures_with_data = []
                 for tool_call_data in tool_calls_list:
@@ -989,19 +1096,24 @@ class ConnectionHandler:
                         f"function_name={tool_call_data['name']}, function_id={tool_call_data['id']}, function_arguments={tool_call_data['arguments']}"
                     )
 
+                    # 使用公共方法上报工具调用
+                    tool_input = json.loads(tool_call_data.get("arguments") or "{}")
+                    enqueue_tool_report(self, tool_call_data['name'], tool_input)
+
                     future = asyncio.run_coroutine_threadsafe(
                         self.func_handler.handle_llm_function_call(
                             self, tool_call_data
                         ),
                         self.loop,
                     )
-                    futures_with_data.append((future, tool_call_data))
+                    futures_with_data.append((future, tool_call_data, tool_input))
 
                 # 工具调用超时时间，可配置，默认30秒
                 tool_call_timeout = int(self.config.get("tool_call_timeout", 30))
                 # 等待协程结束（实际等待时长为最慢的那个）
                 tool_results = []
-                for future, tool_call_data in futures_with_data:
+
+                for future, tool_call_data, tool_input in futures_with_data:
                     try:
                         result = future.result(timeout=tool_call_timeout)
                         tool_results.append((result, tool_call_data))
@@ -1015,7 +1127,10 @@ class ConnectionHandler:
                             tool_call_data
                         ))
 
-                # 统一处理所有工具调用结果
+                    # 使用公共方法上报工具调用结果
+                    enqueue_tool_report(self, tool_call_data['name'], tool_input, str(result.result) if result.result else None, report_tool_call=False)
+
+                # 统一处理工具调用结果
                 if tool_results:
                     self._handle_function_result(tool_results, depth=depth)
 
@@ -1024,6 +1139,11 @@ class ConnectionHandler:
             text_buff = "".join(response_message)
             self.tts_MessageText = text_buff
             self.dialogue.put(Message(role="assistant", content=text_buff))
+
+            # 更新工具调用统计：如果没有调用工具，增加计数
+            if depth == 0 and not tool_call_flag:
+                self.tool_call_stats['consecutive_no_call'] += 1
+
         if depth == 0:
             self.tts.tts_text_queue.put(
                 TTSMessageDTO(
@@ -1039,8 +1159,39 @@ class ConnectionHandler:
                 )
             )
 
+            # 清理临时插入的工具调用提醒消息（使用标记清理）
+            if tool_call_reminder and len(self.dialogue.dialogue) > 0:
+                original_length = len(self.dialogue.dialogue)
+                self.dialogue.dialogue = [
+                    msg for msg in self.dialogue.dialogue
+                    if not getattr(msg, 'is_temporary', False)
+                ]
+                if len(self.dialogue.dialogue) < original_length:
+                    self.logger.bind(tag=TAG).debug("已清理临时的工具调用提醒消息")
+
         return True
 
+    def _get_tool_summary(self, functions: list) -> str:
+        """
+        从工具定义中提取摘要，用于规则强化注入
+
+        Args:
+            functions: 工具列表
+
+        Returns:
+            str: 工具名称字符串
+        """
+        if not functions:
+            return ""
+
+        datas = []
+        for func in functions:
+            func_info = func.get("function", {})
+            name = func_info.get("name", "")
+            datas.append(name)
+        result = "、".join(datas)
+        return result
+
     def _handle_function_result(self, tool_results, depth):
         need_llm_tools = []
 
@@ -1138,9 +1289,9 @@ class ConnectionHandler:
         try:
             # 清理 VAD 连接资源
             if (
-                hasattr(self, "vad")
-                and self.vad
-                and hasattr(self.vad, "release_conn_resources")
+                    hasattr(self, "vad")
+                    and self.vad
+                    and hasattr(self.vad, "release_conn_resources")
             ):
                 self.vad.release_conn_resources(self)
 
@@ -1191,13 +1342,13 @@ class ConnectionHandler:
                 elif self.websocket:
                     try:
                         if (
-                            hasattr(self.websocket, "closed")
-                            and not self.websocket.closed
+                                hasattr(self.websocket, "closed")
+                                and not self.websocket.closed
                         ):
                             await self.websocket.close()
                         elif (
-                            hasattr(self.websocket, "state")
-                            and self.websocket.state.name != "CLOSED"
+                                hasattr(self.websocket, "state")
+                                and self.websocket.state.name != "CLOSED"
                         ):
                             await self.websocket.close()
                         else:

main/xiaozhi-server/core/handle/intentHandler.py

@@ -10,6 +10,7 @@ from core.providers.tts.dto.dto import ContentType
 from core.handle.helloHandle import checkWakeupWords
 from plugins_func.register import Action, ActionResponse
 from core.handle.sendAudioHandle import send_stt_message
+from core.handle.reportHandle import enqueue_tool_report
 from core.utils.util import remove_punctuation_and_length
 from core.providers.tts.dto.dto import TTSMessageDTO, SentenceType
 
@@ -146,6 +147,17 @@ async def process_intent_result(
             await send_stt_message(conn, original_text)
             conn.client_abort = False
 
+            # 准备工具调用参数
+            tool_input = {}
+            if function_args:
+                if isinstance(function_args, str):
+                    tool_input = json.loads(function_args) if function_args else {}
+                elif isinstance(function_args, dict):
+                    tool_input = function_args
+
+            # 上报工具调用
+            enqueue_tool_report(conn, function_name, tool_input)
+
             # 使用executor执行函数调用和结果处理
             def process_function_call():
                 conn.dialogue.put(Message(role="user", content=original_text))
@@ -166,7 +178,10 @@ async def process_intent_result(
                         action=Action.ERROR, result="工具调用超时，请一会再试下哈", response="工具调用超时，请一会再试下哈"
                     )
 
+                # 上报工具调用结果
                 if result:
+                    enqueue_tool_report(conn, function_name, tool_input, str(result.result) if result.result else None, report_tool_call=False)
+
                     if result.action == Action.RESPONSE:  # 直接回复前端
                         text = result.response
                         if text is not None:

main/xiaozhi-server/core/handle/reportHandle.py

@@ -10,6 +10,7 @@ TTS上报功能已集成到ConnectionHandler类中。
 """
 
 import time
+import json
 import opuslib_next
 from typing import TYPE_CHECKING
 
@@ -26,7 +27,7 @@ async def report(conn: "ConnectionHandler", type, text, opus_data, report_time):
 
     Args:
         conn: 连接对象
-        type: 上报类型，1为用户，2为智能体
+        type: 上报类型，1为用户，2为智能体，3为工具调用
         text: 合成文本
         opus_data: opus音频数据
         report_time: 上报时间
@@ -132,6 +133,45 @@ def enqueue_tts_report(conn: "ConnectionHandler", text, opus_data):
         conn.logger.bind(tag=TAG).error(f"加入TTS上报队列失败: {text}, {e}")
 
 
+def enqueue_tool_report(conn: "ConnectionHandler", tool_name: str, tool_input: dict, tool_result: str = None, report_tool_call: bool = True):
+    """将工具调用数据加入上报队列
+
+    Args:
+        conn: 连接对象
+        tool_name: 工具名称
+        tool_input: 工具输入参数
+        tool_result: 工具执行结果（可选）
+        report_tool_call: 是否上报工具调用本身，默认True；仅上报结果时设为False
+    """
+    if not conn.read_config_from_api or conn.need_bind:
+        return
+    if conn.chat_history_conf == 0:
+        return
+
+    try:
+        timestamp = int(time.time())
+
+        # 构建工具调用内容
+        if report_tool_call:
+            tool_text = json.dumps(
+                [
+                    {
+                        "type": "tool",
+                        "text": f"{tool_name}({json.dumps(tool_input, ensure_ascii=False)})",
+                    }
+                ]
+            )
+            conn.report_queue.put((3, tool_text, None, timestamp))
+
+        # 构建工具结果内容
+        if tool_result:
+            result_display = f'{{"result":"{str(tool_result)}"}}'
+            result_content = json.dumps([{"type": "tool_result", "text": result_display}], ensure_ascii=False)
+            conn.report_queue.put((3, result_content, None, timestamp + 1))
+    except Exception as e:
+        conn.logger.bind(tag=TAG).error(f"加入工具上报队列失败: {e}")
+
+
 def enqueue_asr_report(conn: "ConnectionHandler", text, opus_data):
     if not conn.read_config_from_api or conn.need_bind or not conn.report_asr_enable:
         return

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -21,7 +21,6 @@ async def sendAudioMessage(conn: "ConnectionHandler", sentenceType, audios, text
     if conn.tts.tts_audio_first_sentence:
         conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
         conn.tts.tts_audio_first_sentence = False
-        await send_tts_message(conn, "start", None)
 
     if sentenceType == SentenceType.FIRST:
         # 同一句子的后续消息加入流控队列，其他情况立即发送
@@ -204,7 +203,6 @@ def _start_background_sender(conn: "ConnectionHandler", rate_controller, flow_co
 
         conn.last_activity_time = time.time() * 1000
         await _do_send_audio(conn, packet, flow_control)
-        conn.client_is_speaking = True
 
     # 使用 start_sending 启动后台循环
     rate_controller.start_sending(send_callback)
@@ -232,12 +230,10 @@ async def _send_audio_with_rate_control(
         # 预缓冲：前N个包直接发送
         if flow_control["packet_count"] < PRE_BUFFER_COUNT:
             await _do_send_audio(conn, packet, flow_control)
-            conn.client_is_speaking = True
         elif send_delay > 0:
             # 固定延迟模式
             await asyncio.sleep(send_delay)
             await _do_send_audio(conn, packet, flow_control)
-            conn.client_is_speaking = True
         else:
             # 动态流控模式：仅添加到队列，由后台循环负责发送
             rate_controller.add_audio(packet)
@@ -284,6 +280,8 @@ async def send_tts_message(conn: "ConnectionHandler", state, text=None):
             await sendAudio(conn, audios)
         # 等待所有音频包发送完成
         await _wait_for_audio_completion(conn)
+        # 停止音频发送循环
+        conn.audio_rate_controller.stop_sending()
         # 清除服务端讲话状态
         conn.clearSpeakStatus()
 
@@ -318,3 +316,15 @@ async def send_stt_message(conn: "ConnectionHandler", text):
         json.dumps({"type": "stt", "text": stt_text, "session_id": conn.session_id})
     )
     await send_tts_message(conn, "start")
+    # 发送start消息后客户端状态会处于说话中状态，同步服务端状态
+    conn.client_is_speaking = True
+
+
+async def send_display_message(conn: "ConnectionHandler", text):
+    """发送纯显示消息"""
+    message = {
+        "type": "stt",
+        "text": text,
+        "session_id": conn.session_id
+    }
+    await conn.websocket.send(json.dumps(message))

main/xiaozhi-server/core/providers/asr/base.py

@@ -168,10 +168,10 @@ class ASRProviderBase(ABC):
             self.stop_ws_connection()
 
             if text_len > 0:
-                # 使用自定义模块进行上报
-                await startToChat(conn, enhanced_text)
                 audio_snapshot = asr_audio_task.copy()
                 enqueue_asr_report(conn, enhanced_text, audio_snapshot)
+                # 使用自定义模块进行上报
+                await startToChat(conn, enhanced_text)
         except Exception as e:
             logger.bind(tag=TAG).error(f"处理语音停止失败: {e}")
             import traceback

main/xiaozhi-server/core/providers/memory/mem_report_only/mem_report_only.py

@@ -0,0 +1,20 @@
+"""
+仅上报聊天记录，不进行记忆总结
+"""
+
+from ..base import MemoryProviderBase, logger
+
+TAG = __name__
+
+
+class MemoryProvider(MemoryProviderBase):
+    def __init__(self, config, summary_memory=None):
+        super().__init__(config)
+
+    async def save_memory(self, msgs, session_id=None):
+        logger.bind(tag=TAG).debug("mem_report_only mode: No memory saving or summarization is performed.")
+        return None
+
+    async def query_memory(self, query: str) -> str:
+        logger.bind(tag=TAG).debug("mem_report_only mode: No memory query is performed.")
+        return ""

main/xiaozhi-server/core/providers/tools/unified_tool_handler.py

@@ -13,6 +13,7 @@ from .server_mcp import ServerMCPExecutor
 from .device_iot import DeviceIoTExecutor
 from .device_mcp import DeviceMCPExecutor
 from .mcp_endpoint import MCPEndpointExecutor
+from core.handle.sendAudioHandle import send_display_message
 
 
 class UnifiedToolHandler:
@@ -167,6 +168,12 @@ class UnifiedToolHandler:
 
             self.logger.debug(f"调用函数: {function_name}, 参数: {arguments}")
 
+            # 发送工具调用显示消息到设备
+            try:
+                await send_display_message(self.conn, f"% {function_name}")
+            except Exception as e:
+                self.logger.warning(f"发送工具调用显示消息失败: {e}")
+
             # 执行工具调用
             result = await self.tool_manager.execute_tool(function_name, arguments)
             return result

main/xiaozhi-server/core/providers/tts/alibl_stream.py

@@ -33,6 +33,7 @@ class TTSProvider(TTSProviderBase):
         self.api_key = config.get("api_key")
         if not self.api_key:
             raise ValueError("api_key is required for CosyVoice TTS")
+        self.report_on_last = True
 
         # WebSocket配置
         self.ws_url = "wss://dashscope.aliyuncs.com/api-ws/v1/inference/"

main/xiaozhi-server/core/providers/tts/aliyun_stream.py

@@ -104,6 +104,7 @@ class TTSProvider(TTSProviderBase):
         self.access_key_secret = config.get("access_key_secret")
         self.appkey = config.get("appkey")
         self.format = config.get("format", "pcm")
+        self.report_on_last = True
 
         # 音色配置 - CosyVoice大模型音色
         if config.get("private_voice"):

main/xiaozhi-server/core/providers/tts/base.py

@@ -41,6 +41,7 @@ class TTSProviderBase(ABC):
         self.tts_audio_queue = queue.Queue()
         self.tts_audio_first_sentence = True
         self.before_stop_play_files = []
+        self.report_on_last = False
 
         self.tts_text_buff = []
         self.punctuations = (
@@ -323,7 +324,7 @@ class TTSProviderBase(ABC):
     def _audio_play_priority_thread(self):
         # 需要上报的文本和音频列表
         enqueue_text = None
-        enqueue_audio = None
+        enqueue_audio = []
         while not self.conn.stop_event.is_set():
             text = None
             try:
@@ -343,14 +344,24 @@ class TTSProviderBase(ABC):
 
                 # 收到下一个文本开始或会话结束时进行上报
                 if sentence_type is not SentenceType.MIDDLE:
-                    # 上报TTS数据
-                    if enqueue_text is not None and enqueue_audio is not None:
-                        enqueue_tts_report(self.conn, enqueue_text, enqueue_audio)
-                    enqueue_audio = []
-                    enqueue_text = text
+                    if self.report_on_last:
+                        # 累积模式：适用于全程只有一个语音流的TTS（如seed-tts-2.0）
+                        # FIRST时只记录文本，音频持续累积，仅在LAST时统一上报
+                        if text:
+                            enqueue_text = text
+                        if sentence_type == SentenceType.LAST:
+                            enqueue_tts_report(self.conn, enqueue_text, enqueue_audio)
+                            enqueue_audio = []
+                            enqueue_text = None
+                    else:
+                        # 非累积模式：每个句子分别上报
+                        if enqueue_text is not None:
+                            enqueue_tts_report(self.conn, enqueue_text, enqueue_audio)
+                        enqueue_audio = []
+                        enqueue_text = text
 
                 # 收集上报音频数据
-                if isinstance(audio_datas, bytes) and enqueue_audio is not None:
+                if isinstance(audio_datas, bytes):
                     enqueue_audio.append(audio_datas)
 
                 # 发送音频

main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py

@@ -148,6 +148,8 @@ class TTSProvider(TTSProviderBase):
         self.access_token = config.get("access_token")
         self.cluster = config.get("cluster")
         self.resource_id = config.get("resource_id")
+        self.resource_type = True if self.resource_id == "seed-tts-2.0" else False
+        self.report_on_last = self.resource_type
         self.activate_session = False
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
@@ -511,7 +513,7 @@ class TTSProvider(TTSProviderBase):
                     if res.optional.event == EVENT_SessionCanceled:
                         logger.bind(tag=TAG).debug(f"释放服务端资源成功～～")
                         self.activate_session = False
-                    elif res.optional.event == EVENT_TTSSentenceStart:
+                    elif not self.resource_type and res.optional.event == EVENT_TTSSentenceStart:
                         json_data = json.loads(res.payload.decode("utf-8"))
                         self.tts_text = json_data.get("text", "")
                         logger.bind(tag=TAG).debug(f"句子语音生成开始: {self.tts_text}")
@@ -522,8 +524,17 @@ class TTSProvider(TTSProviderBase):
                         res.optional.event == EVENT_TTSResponse
                         and res.header.message_type == AUDIO_ONLY_RESPONSE
                     ):
+                        # 处理seed-tts-2.0文本字幕
+                        if self.resource_type and self.conn.tts_MessageText:
+                            logger.bind(tag=TAG).info(
+                                f"句子语音生成成功： {self.conn.tts_MessageText}"
+                            )
+                            self.tts_audio_queue.put(
+                                (SentenceType.FIRST, [], self.conn.tts_MessageText)
+                            )
+                            self.conn.tts_MessageText = None
                         self.wav_to_opus_data_audio_raw_stream(res.payload, callback=self.handle_opus)
-                    elif res.optional.event == EVENT_TTSSentenceEnd:
+                    elif not self.resource_type and res.optional.event == EVENT_TTSSentenceEnd:
                         logger.bind(tag=TAG).info(f"句子语音生成成功：{self.tts_text}")
                     elif res.optional.event == EVENT_SessionFinished:
                         logger.bind(tag=TAG).debug(f"会话结束～～")

main/xiaozhi-server/core/providers/tts/xunfei_stream.py

@@ -76,6 +76,7 @@ class TTSProvider(TTSProviderBase):
         self.app_id = config.get("app_id")
         self.api_key = config.get("api_key")
         self.api_secret = config.get("api_secret")
+        self.report_on_last = True
 
         # 接口地址
         self.api_url = config.get("api_url", "wss://cbm01.cn-huabei-1.xf-yun.com/v1/private/mcd9m97e6")

main/xiaozhi-server/core/utils/audioRateController.py

@@ -27,6 +27,7 @@ class AudioRateController:
         self.queue_empty_event = asyncio.Event()  # 队列清空事件
         self.queue_empty_event.set()  # 初始为空状态
         self.queue_has_data_event = asyncio.Event()  # 队列数据事件
+        self._last_queue_empty_time = 0  # 上次队列清空的时间（秒）
 
     def reset(self):
         """重置控制器状态"""
@@ -37,12 +38,25 @@ class AudioRateController:
         self.queue.clear()
         self.play_position = 0
         self.start_timestamp = None  # 由首个音频包设置
+        self._last_queue_empty_time = 0  # 重置时间
         # 相关事件处理
         self.queue_empty_event.set()
         self.queue_has_data_event.clear()
 
     def add_audio(self, opus_packet):
         """添加音频包到队列"""
+        # 如果队列之前为空，需要调整时间戳以保持播放时间连续
+        # 这样工具调用等待期间，新加入的音频不会提前播放
+        # 如果间隔很短（<1帧），说明是正常的流式传输，不需要重置
+        if len(self.queue) == 0 and self.play_position > 0:
+            elapsed_since_empty = (time.monotonic() - self._last_queue_empty_time) * 1000
+            # 只有间隔超过1帧时长，才认为是真正的"暂停恢复"
+            if elapsed_since_empty >= self.frame_duration:
+                self.start_timestamp = time.monotonic() - (self.play_position / 1000)
+                self.logger.bind(tag=TAG).debug(
+                    f"队列从空恢复，重置时间戳，当前播放位置: {self.play_position}ms，间隔: {elapsed_since_empty:.0f}ms"
+                )
+
         self.queue.append(("audio", opus_packet))
         # 相关事件处理
         self.queue_empty_event.clear()
@@ -55,6 +69,14 @@ class AudioRateController:
         Args:
             message_callback: 消息发送回调函数 async def()
         """
+        if len(self.queue) == 0 and self.play_position > 0:
+            elapsed_since_empty = (time.monotonic() - self._last_queue_empty_time) * 1000
+            if elapsed_since_empty >= self.frame_duration:
+                self.start_timestamp = time.monotonic() - (self.play_position / 1000)
+                self.logger.bind(tag=TAG).debug(
+                    f"队列从空恢复，重置时间戳，当前播放位置: {self.play_position}ms，间隔: {elapsed_since_empty:.0f}ms"
+                )
+
         self.queue.append(("message", message_callback))
         # 相关事件处理
         self.queue_empty_event.clear()
@@ -126,6 +148,7 @@ class AudioRateController:
         # 队列处理完后清除事件
         self.queue_empty_event.set()
         self.queue_has_data_event.clear()
+        self._last_queue_empty_time = time.monotonic()  # 记录队列清空时间
 
     def start_sending(self, send_audio_callback):
         """

main/xiaozhi-server/core/utils/dialogue.py

@@ -6,18 +6,20 @@ from datetime import datetime
 
 class Message:
     def __init__(
-        self,
-        role: str,
-        content: str = None,
-        uniq_id: str = None,
-        tool_calls=None,
-        tool_call_id=None,
+            self,
+            role: str,
+            content: str = None,
+            uniq_id: str = None,
+            tool_calls=None,
+            tool_call_id=None,
+            is_temporary=False,
     ):
         self.uniq_id = uniq_id if uniq_id is not None else str(uuid.uuid4())
         self.role = role
         self.content = content
         self.tool_calls = tool_calls
         self.tool_call_id = tool_call_id
+        self.is_temporary = is_temporary  # 标记临时消息（如工具调用提醒）
 
 
 class Dialogue:
@@ -59,8 +61,70 @@ class Dialogue:
         else:
             self.put(Message(role="system", content=new_content))
 
+    def trim_history(self, max_turns: int = 10) -> int:
+        """
+        智能截断对话历史，保留工具调用的完整性
+
+        Args:
+            max_turns: 保留的最大对话轮数（每轮 = user + assistant/tool 相关消息）
+
+        Returns:
+            int: 被移除的消息数量
+        """
+        if len(self.dialogue) <= max_turns * 2 + 1:  # +1 是系统消息
+            return 0
+
+        # 分离系统消息和对话消息
+        system_messages = [msg for msg in self.dialogue if msg.role == "system"]
+        conversation_messages = [msg for msg in self.dialogue if msg.role != "system"]
+
+        if len(conversation_messages) <= max_turns * 2:
+            return 0
+
+        # 智能截断：保留完整的工具调用链路
+        keep_messages = []
+        i = len(conversation_messages) - 1
+        turn_count = 0
+
+        while i >= 0 and turn_count < max_turns:
+            msg = conversation_messages[i]
+
+            # 从后向前收集消息
+            if msg.role == "user":
+                # 遇到 user 消息，说明一轮对话开始
+                keep_messages.insert(0, msg)
+                turn_count += 1
+                i -= 1
+            elif msg.role == "assistant":
+                # 收集 assistant 消息
+                keep_messages.insert(0, msg)
+
+                # 如果这个 assistant 有 tool_calls，需要收集对应的 tool 响应
+                if msg.tool_calls is not None:
+                    i -= 1
+                    # 继续向后收集所有相关的 tool 消息
+                    while i >= 0 and conversation_messages[i].role == "tool":
+                        keep_messages.insert(0, conversation_messages[i])
+                        i -= 1
+                else:
+                    i -= 1
+            elif msg.role == "tool":
+                # tool 消息应该已经被上面的逻辑收集了
+                # 如果单独遇到，也要保留（防止边界情况）
+                keep_messages.insert(0, msg)
+                i -= 1
+            else:
+                i -= 1
+
+        removed_count = len(conversation_messages) - len(keep_messages)
+
+        # 重建对话列表
+        self.dialogue = system_messages + keep_messages
+
+        return removed_count
+
     def get_llm_dialogue_with_memory(
-        self, memory_str: str = None, voiceprint_config: dict = None
+            self, memory_str: str = None, voiceprint_config: dict = None
     ) -> List[Dict[str, str]]:
         # 构建对话
         dialogue = []