Enhance system management and audio capture services: implement `SystemStatusResponse` updates with detailed state tracking, add `audio_capture` service creation and lifecycle management, and refactor API `/system` routes for improved status and control handling.

src/VoiceDialogue/api/app.py

@@ -8,7 +8,7 @@ from .core.config import AppConfig
 from .core.lifespan import lifespan
 from .middleware.logging import LoggingMiddleware
 from .middleware.rate_limit import RateLimitMiddleware
-from .routes import tts_routes, asr_routes
+from .routes import tts_routes, asr_routes, system_routes
 
 # 配置日志
 logging.basicConfig(
@@ -56,7 +56,8 @@ def _register_routes(app: FastAPI):
     v1_router = APIRouter(prefix="/api/v1")
     v1_router.include_router(tts_routes.router, prefix="/tts", tags=["TTS模型管理"])
     v1_router.include_router(asr_routes.router, prefix="/asr", tags=["ASR模型管理"])
-
+    v1_router.include_router(system_routes.router, prefix="/system", tags=["系统管理"])
+    
     app.include_router(v1_router)
 
     # 根路径和健康检查

src/VoiceDialogue/api/core/service_factories.py

@@ -1,5 +1,3 @@
-from typing import Any
-
 from services.audio import EchoCancellingAudioCapture, TTSAudioGenerator, AudioStreamPlayer
 from services.audio.audio_generator import BaseTTSConfig, tts_config_registry
 from services.core.constants import (
@@ -127,6 +125,16 @@ def get_core_voice_service_definitions(system_language: str, tts_config: BaseTTS
     ]
 
 
+def get_audio_capture_service_definition() -> ServiceDefinition:
+    """获取音频捕获服务定义"""
+    return ServiceDefinition(
+        name="audio_capture",
+        factory=ServiceFactories.create_audio_capture,
+        dependencies=[],
+        health_check=lambda service: hasattr(service, 'is_ready') and service.is_ready
+    )
+
+
 def get_service_health_checkers() -> dict:
     """获取服务健康检查器映射"""
     return {

src/VoiceDialogue/api/routes/__init__.py

@@ -1,3 +1,3 @@
-from . import tts_routes, asr_routes
+from . import tts_routes, asr_routes, system_routes
 
-__all__ = ["tts_routes", "asr_routes"]
+__all__ = ["tts_routes", "asr_routes", "system_routes"]

src/VoiceDialogue/api/routes/system_routes.py

@@ -2,8 +2,9 @@ import asyncio
 import logging
 import time
 
-from fastapi import APIRouter, HTTPException, BackgroundTasks
+from fastapi import APIRouter, HTTPException, BackgroundTasks, Request
 
+from ..core.service_factories import get_audio_capture_service_definition
 from ..schemas.system_schemas import (
     SystemStatusResponse, SystemConfig,
     SystemStartRequest, SystemResponse
@@ -21,42 +22,54 @@ _system_status = {
 }
 
 
-# @router.get("/status", response_model=SystemStatusResponse, summary="获取系统状态")
-# async def get_system_status():
-#     """
-#     获取系统整体状态，不包含语言模型信息
-#     """
-#     try:
-#         # 获取TTS模型统计
-#         all_configs = tts_config_registry.get_all_configs()
-#         downloaded_count = sum(1 for config in all_configs if config.is_model_complete())
-#
-#         # 获取TTS引擎状态
-#         available_engines = list(tts_manager.list_registered_tts().keys())
-#
-#         status = SystemStatusResponse(
-#             system_status="running",
-#             tts_models_total=len(all_configs),
-#             tts_models_downloaded=downloaded_count,
-#             available_tts_engines=available_engines,
-#             memory_usage=_get_memory_usage(),
-#             disk_usage=_get_disk_usage()
-#         )
-#
-#         return status
-#
-#     except Exception as e:
-#         logger.error(f"获取系统状态失败: {e}", exc_info=True)
-#         raise HTTPException(status_code=500, detail=f"获取系统状态失败: {str(e)}")
+@router.get("/status", response_model=SystemStatusResponse, summary="获取系统状态")
+async def get_system_status(request: Request):
+    """
+    获取系统整体状态，包含服务运行状态
+    """
+    try:
+        # 从应用状态获取服务管理器
+        service_manager = getattr(request.app.state, "service_manager", None)
+        system_running = getattr(request.app.state, "system_running", False)
+
+        # 获取服务状态
+        services_status = {}
+        if service_manager:
+            services_status = service_manager.get_service_status()
+
+        # 检查audio_capture服务状态
+        audio_capture_running = False
+        audio_capture_ready = False
+        if service_manager and service_manager.is_service_running("audio_capture"):
+            audio_capture_service = service_manager.get_service("audio_capture")
+            if audio_capture_service:
+                audio_capture_running = True
+                audio_capture_ready = audio_capture_service.is_ready
+
+        return SystemStatusResponse(
+            status=_system_status["status"],
+            uptime=time.time() - _system_status["start_time"] if _system_status["start_time"] else None,
+            active_sessions=_system_status["active_sessions"],
+            system_running=system_running,
+            services_count=services_status.get("total_services", 0),
+            audio_capture_running=audio_capture_running,
+            audio_capture_ready=audio_capture_ready,
+            services_details=services_status
+        )
+
+    except Exception as e:
+        logger.error(f"获取系统状态失败: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail=f"获取系统状态失败: {str(e)}")
 
 
 @router.post("/start", response_model=SystemResponse, summary="启动系统")
 async def start_system(
         request: SystemStartRequest,
+        fastapi_request: Request,
         background_tasks: BackgroundTasks
 ):
     """
-    启动语音对话系统
+    启动语音对话系统 - 创建audio_capture服务
     """
     try:
         if _system_status["status"] in ["running", "starting"]:
@@ -72,7 +85,8 @@ async def start_system(
         # 在后台启动系统
         background_tasks.add_task(
             _start_system_background,
-            request.config
+            request.config,
+            fastapi_request
         )
 
         return SystemResponse(
@@ -87,9 +101,9 @@ async def start_system(
 
 
 @router.post("/stop", response_model=SystemResponse, summary="停止系统")
-async def stop_system():
+async def stop_system(request: Request):
     """
-    停止语音对话系统
+    停止语音对话系统 - 停止audio_capture服务
     """
     try:
         if _system_status["status"] == "stopped":
@@ -101,8 +115,29 @@ async def stop_system():
         # 更新状态
         _system_status["status"] = "stopping"
 
-        # 模拟停止过程
-        await asyncio.sleep(1)
+        # 获取服务管理器
+        service_manager = getattr(request.app.state, "service_manager", None)
+        if service_manager:
+            # 停止audio_capture服务
+            if service_manager.is_service_running("audio_capture"):
+                audio_capture_service = service_manager.get_service("audio_capture")
+                if audio_capture_service:
+                    try:
+                        audio_capture_service.stop()
+                        logger.info("音频捕获服务已停止")
+
+                        # 等待服务停止
+                        timeout = 5
+                        start_time = time.time()
+                        while audio_capture_service.is_alive() and (time.time() - start_time) < timeout:
+                            await asyncio.sleep(0.1)
+
+                        # 从服务管理器中移除
+                        if "audio_capture" in service_manager.services:
+                            del service_manager.services["audio_capture"]
+
+                    except Exception as e:
+                        logger.error(f"停止音频捕获服务时发生错误: {e}", exc_info=True)
 
         _system_status["status"] = "stopped"
         _system_status["start_time"] = None
@@ -122,6 +157,7 @@ async def stop_system():
 @router.post("/restart", response_model=SystemResponse, summary="重启系统")
 async def restart_system(
         request: SystemStartRequest,
+        fastapi_request: Request,
         background_tasks: BackgroundTasks
 ):
     """
@@ -130,28 +166,41 @@ async def restart_system(
     try:
         # 先停止
         if _system_status["status"] != "stopped":
-            await stop_system()
+            await stop_system(fastapi_request)
 
         # 再启动
-        return await start_system(request, background_tasks)
+        return await start_system(request, fastapi_request, background_tasks)
 
     except Exception as e:
         logger.error(f"系统重启失败: {e}", exc_info=True)
         raise HTTPException(status_code=500, detail=f"系统重启失败: {str(e)}")
 
 
-async def _start_system_background(config: SystemConfig):
+async def _start_system_background(config: SystemConfig, request: Request):
     """
-    后台启动系统的实际逻辑
+    后台启动系统的实际逻辑 - 创建并启动audio_capture服务
     """
     try:
         logger.info("开始启动语音对话系统...")
 
-        # 模拟启动过程
-        await asyncio.sleep(2)
+        # 获取服务管理器
+        service_manager = getattr(request.app.state, "service_manager", None)
+        if not service_manager:
+            raise RuntimeError("服务管理器未初始化")
+
+        # 检查audio_capture服务是否已存在
+        if service_manager.is_service_running("audio_capture"):
+            logger.info("音频捕获服务已在运行")
+        else:
+            # 创建audio_capture服务定义
+            audio_capture_def = get_audio_capture_service_definition()
+
+            # 启动audio_capture服务
+            success = service_manager.start_service(audio_capture_def)
+            if not success:
+                raise RuntimeError("音频捕获服务启动失败")
 
-        # 这里应该调用实际的系统启动逻辑
-        # 类似于原来main.py中的launch_system函数
+            logger.info("音频捕获服务启动成功")
 
         _system_status["status"] = "running"
         _system_status["start_time"] = time.time()

src/VoiceDialogue/api/schemas/system_schemas.py

@@ -1,22 +1,25 @@
-from typing import Optional, Literal
+from typing import Optional, Literal, Dict, Any
 
 from pydantic import BaseModel, Field
 
 
 class SystemStatusResponse(BaseModel):
-    """系统状态"""
+    """系统状态响应"""
     status: Literal['running', 'stopped', 'starting', 'stopping'] = Field(..., description="系统状态")
     uptime: Optional[float] = Field(None, description="运行时间(秒)")
     active_sessions: int = Field(default=0, description="活跃会话数")
-    memory_usage: Optional[float] = Field(None, description="内存使用率")
+    system_running: bool = Field(default=False, description="系统是否运行中")
+    services_count: int = Field(default=0, description="运行中的服务数量")
+    audio_capture_running: bool = Field(default=False, description="音频捕获服务是否运行")
+    audio_capture_ready: bool = Field(default=False, description="音频捕获服务是否就绪")
+    services_details: Optional[Dict[str, Any]] = Field(None, description="服务详细状态信息")
 
 
 class SystemConfig(BaseModel):
     """系统配置"""
-    user_language: Literal['zh', 'en'] = Field(default='zh', description="用户语言")
-    system_prompt: str = Field(..., description="系统提示词")
-    tts_speaker: str = Field(default='沈逸', description="TTS语音角色")
-    llm_model: Literal['7B', '14B'] = Field(default='14B', description="语言模型规模")
+    language: Optional[str] = Field(default="zh", description="系统语言")
+    sample_rate: Optional[int] = Field(default=16000, description="音频采样率")
+    enable_logging: Optional[bool] = Field(default=True, description="是否启用日志")
 
 
 class SystemStartRequest(BaseModel):
@@ -25,7 +28,6 @@ class SystemStartRequest(BaseModel):
 
 
 class SystemResponse(BaseModel):
-    """系统响应"""
+    """系统操作响应"""
     success: bool = Field(..., description="操作是否成功")
     message: str = Field(..., description="响应消息")
-    status: Optional[SystemStatusResponse] = Field(None, description="系统状态")