neuro-simulator 0.0.1__tar.gz

neuro_simulator-0.0.1/PKG-INFO

@@ -0,0 +1,193 @@
+Metadata-Version: 2.4
+Name: neuro-simulator
+Version: 0.0.1
+Summary: Neuro Simulator Server
+Home-page: https://github.com/Moha-Master/neuro-simulator
+Author: Moha-Master
+Author-email: hongkongreporter@outlook.com
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: fastapi
+Requires-Dist: uvicorn
+Requires-Dist: google-genai
+Requires-Dist: azure-cognitiveservices-speech
+Requires-Dist: letta-client
+Requires-Dist: openai
+Requires-Dist: pyyaml
+Requires-Dist: pydantic
+Requires-Dist: jinja2
+Requires-Dist: python-multipart
+Requires-Dist: mutagen
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Neuro-Simulator 服务端
+
+*关注Vedal喵，关注Vedal谢谢喵*
+
+*本临时README由AI自动生成*
+
+这是 Neuro Simulator 的后端服务，基于 Python 和 FastAPI 构建，负责处理直播逻辑、AI 交互、TTS 合成等核心功能。
+
+## 功能特性
+
+- **多 LLM 支持**：支持 Gemini 和 OpenAI API，用于生成观众聊天内容
+- **配置管理**：支持通过 API 动态修改和热重载配置
+- **外部控制**：完全使用外部API端点操控服务端运行
+
+## 目录结构
+
+```
+neuro_simulator/
+├── main.py              # 应用入口和核心逻辑
+├── config.py            # 配置管理模块
+├── letta.py             # Letta Agent 集成
+├── chatbot.py           # 观众聊天生成器
+├── audio_synthesis.py   # 音频合成模块
+├── stream_chat.py       # 聊天消息处理
+├── stream_manager.py    # 直播管理器
+├── websocket_manager.py # WebSocket 连接管理
+├── process_manager.py   # 进程管理器
+├── shared_state.py      # 全局状态管理
+├── log_handler.py       # 日志处理模块
+├── requirements.txt     # Python 依赖列表
+├── setup.py             # Python 包安装配置
+├── cli.py               # 命令行启动脚本
+├── settings.yaml.example # 自带的备用配置模板
+└── media/               # 自带的备用媒体文件
+    └── neuro_start.mp4  # 用来计算Start Soon长度，仅读取时长
+```
+
+```
+working_dir_example/     # 工作目录结构
+├── media/               # 媒体文件夹，如缺失会使用自带资源覆盖
+│   └── neuro_start.mp4  # 用来计算Start Soon长度，仅读取时长
+├── settings.yaml        # 由用户手工创建的配置文件
+└── settings.yaml.example # 自动生成的配置文件模板，必须手动重命名和填写
+```
+
+## 安装与配置
+
+0. **配置设置**
+   复制一份 `working_dir_example` 到你想要的位置，作为配置文件目录
+   然后进入配置文件目录，复制 `settings.yaml.example` 到 `settings.yaml`
+   编辑 `settings.yaml` 文件，填入必要的 API 密钥和配置项：
+   - Letta Token 和 Agent ID
+   - Gemini/OpenAI API Key
+   - Azure TTS Key 和 Region
+   可以执行替换media/neuro_start.mp4为其它视频文件，但记得手动替换client中的同名文件
+
+### 方法一：使用 pip 安装
+
+1. **从云端安装PyPi包，适合直接使用**
+   ```bash
+   python3 -m venv venv
+   # Windows
+   venv/Scripts/pip install neuro-simulator
+   # macOS/Linux
+   venv/bin/pip install neuro-simulator
+   ```
+
+   **从本地安装PyPi包，适合二次开发**
+   ```bash
+   python3 -m venv venv
+   #Windows
+   venv/Scripts/pip install -e .
+   # macOS/Linux
+   venv/bin/pip install -e .
+   ```
+
+2. **运行服务**
+   ```bash
+   # 使用默认配置 (~/.config/neuro-simulator/)
+   neuro
+   
+   # 指定工作目录
+   neuro -D /path/to/your/config
+   
+   # 指定主机和端口
+   neuro -H 0.0.0.0 -P 8080
+   
+   # 组合使用
+   neuro -D /path/to/your/config -H 0.0.0.0 -P 8080
+   ```
+
+### 方法二：传统方式运行
+
+1. **创建并激活虚拟环境**
+   ```bash
+   python -m venv venv
+   # Windows
+   venv\Scripts\activate
+   # macOS/Linux
+   source venv/bin/activate
+   ```
+
+2. **安装依赖**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. **启动服务**
+   ```bash
+   uvicorn main:app --host 127.0.0.1 --port 8000
+   ```
+
+服务默认运行在 `http://127.0.0.1:8000`。
+
+## API 接口
+
+后端提供丰富的 API 接口用于控制和管理：
+
+- `/api/stream/*` - 直播控制接口（启动/停止/重启/状态）
+- `/api/configs/*` - 配置管理接口（获取/更新/重载配置）
+  - `api_keys` `server` 等敏感配置项无法从接口获取和修改。
+- `/api/logs` - 日志获取接口
+- `/api/tts/synthesize` - TTS 合成接口
+- `/api/system/health` - 健康检查接口
+- `/ws/stream` - 直播内容 WebSocket 接口
+- `/ws/logs` - 日志流 WebSocket 接口
+
+详细接口说明可通过 `http://127.0.0.1:8000/docs` 访问 API 文档查看。
+
+## 配置说明
+
+配置文件 `settings.yaml` 包含以下主要配置项：
+
+- `api_keys` - 各种服务的 API 密钥
+- `stream_metadata` - 直播元数据（标题、分类、标签等）
+- `neuro_behavior` - Neuro 行为设置
+- `audience_simulation` - 观众模拟设置
+- `tts` - TTS 语音合成设置
+- `performance` - 性能相关设置
+- `server` - 服务器设置（主机、端口、CORS 等）
+
+## 安全说明
+
+1. 通过 `panel_password` 配置项可以设置控制面板访问密码
+2. 敏感配置项（如 API 密钥）不会通过 API 接口暴露
+3. 支持 CORS，但仅允许预配置的来源访问
+
+## 故障排除
+
+- 确保所有必需的 API 密钥都已正确配置
+- 检查网络连接是否正常
+- 查看日志文件获取错误信息
+- 确保端口未被其他程序占用 

neuro_simulator-0.0.1/README.md

@@ -0,0 +1,153 @@
+# Neuro-Simulator 服务端
+
+*关注Vedal喵，关注Vedal谢谢喵*
+
+*本临时README由AI自动生成*
+
+这是 Neuro Simulator 的后端服务，基于 Python 和 FastAPI 构建，负责处理直播逻辑、AI 交互、TTS 合成等核心功能。
+
+## 功能特性
+
+- **多 LLM 支持**：支持 Gemini 和 OpenAI API，用于生成观众聊天内容
+- **配置管理**：支持通过 API 动态修改和热重载配置
+- **外部控制**：完全使用外部API端点操控服务端运行
+
+## 目录结构
+
+```
+neuro_simulator/
+├── main.py              # 应用入口和核心逻辑
+├── config.py            # 配置管理模块
+├── letta.py             # Letta Agent 集成
+├── chatbot.py           # 观众聊天生成器
+├── audio_synthesis.py   # 音频合成模块
+├── stream_chat.py       # 聊天消息处理
+├── stream_manager.py    # 直播管理器
+├── websocket_manager.py # WebSocket 连接管理
+├── process_manager.py   # 进程管理器
+├── shared_state.py      # 全局状态管理
+├── log_handler.py       # 日志处理模块
+├── requirements.txt     # Python 依赖列表
+├── setup.py             # Python 包安装配置
+├── cli.py               # 命令行启动脚本
+├── settings.yaml.example # 自带的备用配置模板
+└── media/               # 自带的备用媒体文件
+    └── neuro_start.mp4  # 用来计算Start Soon长度，仅读取时长
+```
+
+```
+working_dir_example/     # 工作目录结构
+├── media/               # 媒体文件夹，如缺失会使用自带资源覆盖
+│   └── neuro_start.mp4  # 用来计算Start Soon长度，仅读取时长
+├── settings.yaml        # 由用户手工创建的配置文件
+└── settings.yaml.example # 自动生成的配置文件模板，必须手动重命名和填写
+```
+
+## 安装与配置
+
+0. **配置设置**
+   复制一份 `working_dir_example` 到你想要的位置，作为配置文件目录
+   然后进入配置文件目录，复制 `settings.yaml.example` 到 `settings.yaml`
+   编辑 `settings.yaml` 文件，填入必要的 API 密钥和配置项：
+   - Letta Token 和 Agent ID
+   - Gemini/OpenAI API Key
+   - Azure TTS Key 和 Region
+   可以执行替换media/neuro_start.mp4为其它视频文件，但记得手动替换client中的同名文件
+
+### 方法一：使用 pip 安装
+
+1. **从云端安装PyPi包，适合直接使用**
+   ```bash
+   python3 -m venv venv
+   # Windows
+   venv/Scripts/pip install neuro-simulator
+   # macOS/Linux
+   venv/bin/pip install neuro-simulator
+   ```
+
+   **从本地安装PyPi包，适合二次开发**
+   ```bash
+   python3 -m venv venv
+   #Windows
+   venv/Scripts/pip install -e .
+   # macOS/Linux
+   venv/bin/pip install -e .
+   ```
+
+2. **运行服务**
+   ```bash
+   # 使用默认配置 (~/.config/neuro-simulator/)
+   neuro
+   
+   # 指定工作目录
+   neuro -D /path/to/your/config
+   
+   # 指定主机和端口
+   neuro -H 0.0.0.0 -P 8080
+   
+   # 组合使用
+   neuro -D /path/to/your/config -H 0.0.0.0 -P 8080
+   ```
+
+### 方法二：传统方式运行
+
+1. **创建并激活虚拟环境**
+   ```bash
+   python -m venv venv
+   # Windows
+   venv\Scripts\activate
+   # macOS/Linux
+   source venv/bin/activate
+   ```
+
+2. **安装依赖**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. **启动服务**
+   ```bash
+   uvicorn main:app --host 127.0.0.1 --port 8000
+   ```
+
+服务默认运行在 `http://127.0.0.1:8000`。
+
+## API 接口
+
+后端提供丰富的 API 接口用于控制和管理：
+
+- `/api/stream/*` - 直播控制接口（启动/停止/重启/状态）
+- `/api/configs/*` - 配置管理接口（获取/更新/重载配置）
+  - `api_keys` `server` 等敏感配置项无法从接口获取和修改。
+- `/api/logs` - 日志获取接口
+- `/api/tts/synthesize` - TTS 合成接口
+- `/api/system/health` - 健康检查接口
+- `/ws/stream` - 直播内容 WebSocket 接口
+- `/ws/logs` - 日志流 WebSocket 接口
+
+详细接口说明可通过 `http://127.0.0.1:8000/docs` 访问 API 文档查看。
+
+## 配置说明
+
+配置文件 `settings.yaml` 包含以下主要配置项：
+
+- `api_keys` - 各种服务的 API 密钥
+- `stream_metadata` - 直播元数据（标题、分类、标签等）
+- `neuro_behavior` - Neuro 行为设置
+- `audience_simulation` - 观众模拟设置
+- `tts` - TTS 语音合成设置
+- `performance` - 性能相关设置
+- `server` - 服务器设置（主机、端口、CORS 等）
+
+## 安全说明
+
+1. 通过 `panel_password` 配置项可以设置控制面板访问密码
+2. 敏感配置项（如 API 密钥）不会通过 API 接口暴露
+3. 支持 CORS，但仅允许预配置的来源访问
+
+## 故障排除
+
+- 确保所有必需的 API 密钥都已正确配置
+- 检查网络连接是否正常
+- 查看日志文件获取错误信息
+- 确保端口未被其他程序占用 

neuro_simulator-0.0.1/neuro_simulator/__init__.py

@@ -0,0 +1 @@
+# neuro_simulator/__init__.py

neuro_simulator-0.0.1/neuro_simulator/audio_synthesis.py

@@ -0,0 +1,66 @@
+# backend/audio_synthesis.py
+import html
+import base64
+import azure.cognitiveservices.speech as speechsdk
+import asyncio
+from .config import config_manager
+
+async def synthesize_audio_segment(text: str, voice_name: str = None, pitch: float = None) -> tuple[str, float]:
+    """
+    使用 Azure TTS 合成音频。
+    如果 voice_name 或 pitch 未提供，则使用配置中的默认值。
+    返回 Base64 编码的音频字符串和音频时长（秒）。
+    """
+    # 使用 config_manager.settings 中的值
+    azure_key = config_manager.settings.api_keys.azure_speech_key
+    azure_region = config_manager.settings.api_keys.azure_speech_region
+    
+    if not azure_key or not azure_region:
+        raise ValueError("Azure Speech Key 或 Region 未在配置中设置。")
+
+    # 如果未传入参数，则使用配置的默认值
+    final_voice_name = voice_name if voice_name is not None else config_manager.settings.tts.voice_name
+    final_pitch = pitch if pitch is not None else config_manager.settings.tts.voice_pitch
+
+    speech_config = speechsdk.SpeechConfig(subscription=azure_key, region=azure_region)
+    speech_config.set_speech_synthesis_output_format(speechsdk.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3)
+
+    pitch_percent = int((final_pitch - 1.0) * 100)
+    pitch_ssml_value = f"+{pitch_percent}%" if pitch_percent >= 0 else f"{pitch_percent}%"
+    
+    escaped_text = html.escape(text)
+
+    ssml_string = f"""
+    <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US">
+        <voice name="{final_voice_name}">
+            <prosody pitch="{pitch_ssml_value}">
+                {escaped_text}
+            </prosody>
+        </voice>
+    </speak>
+    """
+    
+    synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=None)
+
+    def _perform_synthesis_sync():
+        return synthesizer.speak_ssml_async(ssml_string).get()
+
+    try:
+        result = await asyncio.to_thread(_perform_synthesis_sync)
+
+        if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
+            audio_data = result.audio_data
+            encoded_audio = base64.b64encode(audio_data).decode('utf-8')
+            audio_duration_sec = result.audio_duration.total_seconds()
+            print(f"TTS 合成完成: '{text[:30]}...' (时长: {audio_duration_sec:.2f}s)")
+            return encoded_audio, audio_duration_sec
+        else:
+            cancellation_details = result.cancellation_details
+            error_message = f"TTS 合成失败/取消 (原因: {cancellation_details.reason})。文本: '{text}'"
+            if cancellation_details.error_details:
+                error_message += f" | 详情: {cancellation_details.error_details}"
+            print(f"错误: {error_message}")
+            raise Exception(error_message)
+    except Exception as e:
+        print(f"错误: 在调用 Azure TTS SDK 时发生异常: {e}")
+        raise

neuro_simulator-0.0.1/neuro_simulator/chatbot.py

@@ -0,0 +1,104 @@
+# backend/chatbot.py
+from google import genai
+from google.genai import types
+from openai import AsyncOpenAI
+import random
+import asyncio
+from .config import config_manager, AppSettings
+import neuro_simulator.shared_state as shared_state
+
+class AudienceLLMClient:
+    async def generate_chat_messages(self, prompt: str, max_tokens: int) -> str:
+        raise NotImplementedError
+
+class GeminiAudienceLLM(AudienceLLMClient):
+    def __init__(self, api_key: str, model_name: str):
+        if not api_key:
+            raise ValueError("Gemini API Key is not provided for GeminiAudienceLLM.")
+        # 根据新文档，正确初始化客户端
+        self.client = genai.Client(api_key=api_key)
+        self.model_name = model_name
+        print(f"已初始化 GeminiAudienceLLM (new SDK)，模型: {self.model_name}")
+
+    async def generate_chat_messages(self, prompt: str, max_tokens: int) -> str:
+        # 根据新文档，使用正确的异步方法和参数
+        response = await self.client.aio.models.generate_content(
+            model=self.model_name,
+            contents=prompt,
+            config=types.GenerateContentConfig(
+                temperature=config_manager.settings.audience_simulation.llm_temperature,
+                max_output_tokens=max_tokens
+            )
+        )
+        raw_chat_text = ""
+        if hasattr(response, 'text') and response.text:
+            raw_chat_text = response.text
+        elif response.candidates and response.candidates[0].content and response.candidates[0].content.parts:
+            for part in response.candidates[0].content.parts:
+                if hasattr(part, 'text') and part.text:
+                    raw_chat_text += part.text
+        return raw_chat_text
+
+class OpenAIAudienceLLM(AudienceLLMClient):
+    def __init__(self, api_key: str, model_name: str, base_url: str | None):
+        if not api_key:
+            raise ValueError("OpenAI API Key is not provided for OpenAIAudienceLLM.")
+        self.client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+        self.model_name = model_name
+        print(f"已初始化 OpenAIAudienceLLM，模型: {self.model_name}，API Base: {base_url}")
+
+    async def generate_chat_messages(self, prompt: str, max_tokens: int) -> str:
+        response = await self.client.chat.completions.create(
+            model=self.model_name,
+            messages=[{"role": "user", "content": prompt}],
+            temperature=config_manager.settings.audience_simulation.llm_temperature,
+            max_tokens=max_tokens,
+        )
+        if response.choices and response.choices[0].message and response.choices[0].message.content:
+            return response.choices[0].message.content.strip()
+        return ""
+
+async def get_dynamic_audience_prompt() -> str:
+    current_neuro_speech = ""
+    async with shared_state.neuro_last_speech_lock:
+        current_neuro_speech = shared_state.neuro_last_speech
+    
+    # 使用 settings 对象中的模板和变量
+    prompt = config_manager.settings.audience_simulation.prompt_template.format(
+        neuro_speech=current_neuro_speech,
+        num_chats_to_generate=config_manager.settings.audience_simulation.chats_per_batch
+    )
+    return prompt
+
+class ChatbotManager:
+    def __init__(self):
+        self.client: AudienceLLMClient = self._create_client(config_manager.settings)
+        self._last_checked_settings: dict = config_manager.settings.audience_simulation.model_dump()
+        print("ChatbotManager initialized.")
+
+    def _create_client(self, settings: AppSettings) -> AudienceLLMClient:
+        provider = settings.audience_simulation.llm_provider
+        print(f"正在为 provider 创建新的 audience LLM client: {provider}")
+        if provider.lower() == "gemini":
+            if not settings.api_keys.gemini_api_key:
+                raise ValueError("GEMINI_API_KEY 未在配置中设置")
+            return GeminiAudienceLLM(api_key=settings.api_keys.gemini_api_key, model_name=settings.audience_simulation.gemini_model)
+        elif provider.lower() == "openai":
+            if not settings.api_keys.openai_api_key:
+                raise ValueError("OPENAI_API_KEY 未在配置中设置")
+            return OpenAIAudienceLLM(api_key=settings.api_keys.openai_api_key, model_name=settings.audience_simulation.openai_model, base_url=settings.api_keys.openai_api_base_url)
+        else:
+            raise ValueError(f"不支持的 AUDIENCE_LLM_PROVIDER: {provider}")
+
+    def handle_config_update(self, new_settings: AppSettings):
+        new_audience_settings = new_settings.audience_simulation.model_dump()
+        if new_audience_settings != self._last_checked_settings:
+            print("检测到观众模拟设置已更改，正在重新初始化 LLM client...")
+            try:
+                self.client = self._create_client(new_settings)
+                self._last_checked_settings = new_audience_settings
+                print("LLM client 已成功热重载。")
+            except Exception as e:
+                print(f"错误：热重载 LLM client 失败: {e}")
+        else:
+            print("观众模拟设置未更改，跳过 LLM client 重载。")

neuro_simulator-0.0.1/neuro_simulator/cli.py

@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+
+import argparse
+import os
+import sys
+import shutil
+from pathlib import Path
+
+def main():
+    parser = argparse.ArgumentParser(description="Neuro-Simulator Server")
+    parser.add_argument("-D", "--dir", help="Working directory containing settings.yaml")
+    parser.add_argument("-H", "--host", help="Host to bind the server to")
+    parser.add_argument("-P", "--port", type=int, help="Port to bind the server to")
+    
+    args = parser.parse_args()
+    
+    # Set working directory
+    if args.dir:
+        work_dir = Path(args.dir).resolve()
+        # If the directory doesn't exist (and it's not the default), raise an error
+        if not work_dir.exists():
+            print(f"Error: Working directory '{work_dir}' does not exist. Please create it manually.")
+            sys.exit(1)
+    else:
+        work_dir = Path.home() / ".config" / "neuro-simulator"
+        work_dir.mkdir(parents=True, exist_ok=True)
+    
+    # Change to working directory
+    os.chdir(work_dir)
+    
+    # Handle settings.yaml.example
+    settings_example_path = work_dir / "settings.yaml.example"
+    settings_path = work_dir / "settings.yaml"
+    
+    # Copy settings.yaml.example from package if it doesn't exist
+    if not settings_example_path.exists():
+        try:
+            # Try pkg_resources first (for installed packages)
+            try:
+                import pkg_resources
+                example_path = pkg_resources.resource_filename('neuro_simulator', 'settings.yaml.example')
+                if os.path.exists(example_path):
+                    shutil.copy(example_path, settings_example_path)
+                    print(f"Created {settings_example_path} from package example")
+                else:
+                    # Fallback to relative path (for development mode)
+                    dev_example_path = Path(__file__).parent / "settings.yaml.example"
+                    if dev_example_path.exists():
+                        shutil.copy(dev_example_path, settings_example_path)
+                        print(f"Created {settings_example_path} from development example")
+                    else:
+                        print("Warning: settings.yaml.example not found in package or development folder")
+            except Exception:
+                # Fallback to relative path (for development mode)
+                dev_example_path = Path(__file__).parent / "settings.yaml.example"
+                if dev_example_path.exists():
+                    shutil.copy(dev_example_path, settings_example_path)
+                    print(f"Created {settings_example_path} from development example")
+                else:
+                    print("Warning: settings.yaml.example not found in package or development folder")
+        except Exception as e:
+            print(f"Warning: Could not copy settings.yaml.example from package: {e}")
+    
+    # Handle media folder
+    media_dir = work_dir / "media"
+    video_path = media_dir / "neuro_start.mp4"
+    
+    # Copy media folder from package if it doesn't exist or is invalid
+    if not media_dir.exists() or not video_path.exists():
+        # If media dir exists but video doesn't, remove the incomplete media dir
+        if media_dir.exists():
+            shutil.rmtree(media_dir)
+            
+        try:
+            # Try pkg_resources first (for installed packages)
+            try:
+                import pkg_resources
+                package_media_path = pkg_resources.resource_filename('neuro_simulator', 'media')
+                if os.path.exists(package_media_path):
+                    shutil.copytree(package_media_path, media_dir)
+                    print(f"Created {media_dir} from package media")
+                else:
+                    # Fallback to relative path (for development mode)
+                    dev_media_path = Path(__file__).parent / "media"
+                    if dev_media_path.exists():
+                        shutil.copytree(dev_media_path, media_dir)
+                        print(f"Created {media_dir} from development media")
+                    else:
+                        print("Warning: media folder not found in package or development folder")
+            except Exception:
+                # Fallback to relative path (for development mode)
+                dev_media_path = Path(__file__).parent / "media"
+                if dev_media_path.exists():
+                    shutil.copytree(dev_media_path, media_dir)
+                    print(f"Created {media_dir} from development media")
+                else:
+                    print("Warning: media folder not found in package or development folder")
+        except Exception as e:
+            print(f"Warning: Could not copy media folder from package: {e}")
+    
+    # Now check for required files and handle errors appropriately
+    errors = []
+    
+    # Check for settings.yaml (required for running)
+    if not settings_path.exists():
+        if settings_example_path.exists():
+            errors.append(f"Error: {settings_path} not found. Please copy {settings_example_path} to {settings_path} and configure it.")
+        else:
+            errors.append(f"Error: Neither {settings_path} nor {settings_example_path} found. Please ensure proper configuration.")
+    
+    # Check for required media files (required for running)
+    if not media_dir.exists() or not video_path.exists():
+        errors.append(f"Error: Required media files not found in {media_dir}.")
+    
+    # If there are any errors, print them and exit
+    if errors:
+        for error in errors:
+            print(error)
+        sys.exit(1)
+    
+    # Import and run the main application
+    try:
+        from neuro_simulator.main import run_server
+        run_server(args.host, args.port)
+    except ImportError:
+        # Fallback for development mode
+        sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+        from neuro_simulator.main import run_server
+        run_server(args.host, args.port)
+
+if __name__ == "__main__":
+    main()