CodeReview/example.txt

110 lines
4.2 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ========================================
# XCodeReviewer 环境变量配置示例
# ========================================
# 复制此文件为 .env 并填写你的配置
# ==================== LLM 通用配置 ====================
# 选择你想使用的LLM提供商 (gemini|openai|claude|qwen|deepseek|zhipu|moonshot|baidu|minimax|doubao|ollama)
VITE_LLM_PROVIDER=gemini
# 通用LLM配置 (可选,如果设置了这些,会覆盖下面的特定平台配置)
# VITE_LLM_API_KEY=your_api_key_here
# VITE_LLM_MODEL=your_model_name
# VITE_LLM_BASE_URL=https://custom-api-endpoint.com
# VITE_LLM_TIMEOUT=150000
# VITE_LLM_TEMPERATURE=0.2
# VITE_LLM_MAX_TOKENS=4096
# ==================== Google Gemini 配置 ====================
# 获取API Key: https://makersuite.google.com/app/apikey
# VITE_GEMINI_API_KEY=your_gemini_api_key_here
# VITE_GEMINI_MODEL=gemini-2.5-flash
# VITE_GEMINI_TIMEOUT_MS=150000
# ==================== OpenAI 配置 ====================
# 获取API Key: https://platform.openai.com/api-keys
# VITE_OPENAI_API_KEY=your_openai_api_key_here
# VITE_OPENAI_MODEL=gpt-4o-mini
# VITE_OPENAI_BASE_URL=https://api.openai.com/v1
# ==================== Anthropic Claude 配置 ====================
# 获取API Key: https://console.anthropic.com/
# VITE_CLAUDE_API_KEY=your_claude_api_key_here
# VITE_CLAUDE_MODEL=claude-3-5-sonnet-20241022
# ==================== 阿里云通义千问 配置 ====================
# 获取API Key: https://dashscope.console.aliyun.com/
# VITE_QWEN_API_KEY=your_qwen_api_key_here
# VITE_QWEN_MODEL=qwen-turbo
# ==================== DeepSeek 配置 ====================
# 获取API Key: https://platform.deepseek.com/
# VITE_DEEPSEEK_API_KEY=your_deepseek_api_key_here
# VITE_DEEPSEEK_MODEL=deepseek-chat
# ==================== 智谱AI (GLM) 配置 ====================
# 获取API Key: https://open.bigmodel.cn/
# VITE_ZHIPU_API_KEY=your_zhipu_api_key_here
# VITE_ZHIPU_MODEL=glm-4-flash
# ==================== 月之暗面 Kimi 配置 ====================
# 获取API Key: https://platform.moonshot.cn/
# VITE_MOONSHOT_API_KEY=your_moonshot_api_key_here
# VITE_MOONSHOT_MODEL=moonshot-v1-8k
# ==================== 百度文心一言 配置 ====================
# 获取API Key: https://console.bce.baidu.com/qianfan/
# 注意百度API Key格式为 "API_KEY:SECRET_KEY"
# VITE_BAIDU_API_KEY=your_api_key:your_secret_key
# VITE_BAIDU_MODEL=ERNIE-3.5-8K
# ==================== MiniMax 配置 ====================
# 获取API Key: https://www.minimaxi.com/
# VITE_MINIMAX_API_KEY=your_minimax_api_key_here
# VITE_MINIMAX_MODEL=abab6.5-chat
# ==================== 字节豆包 配置 ====================
# 获取API Key: https://console.volcengine.com/ark
# 注意豆包使用endpoint ID需要先创建推理接入点
# VITE_DOUBAO_API_KEY=your_doubao_api_key_here
# VITE_DOUBAO_MODEL=doubao-pro-32k
# ==================== Ollama 本地大模型配置 ====================
# Ollama 允许在本地运行开源大模型,无需 API Key
# 安装: https://ollama.com/
# 快速开始:
# 1. 安装 Ollama: curl -fsSL https://ollama.com/install.sh | sh
# 2. 下载模型: ollama pull llama3
# 3. 配置如下并启动应用
# VITE_OLLAMA_API_KEY=ollama # 本地运行不需要真实Key填写任意值
# VITE_OLLAMA_MODEL=llama3
# VITE_OLLAMA_BASE_URL=http://localhost:11434/v1
#
# 推荐模型:
# - llama3 (综合能力强,适合各种任务)
# - codellama (代码专用,适合代码审查)
# - qwen2.5:7b (中文支持好)
# - deepseek-coder (代码理解能力强)
# - phi3:mini (轻量级,速度快)
#
# 更多模型: https://ollama.com/library
# ==================== Supabase 数据库配置 (可选) ====================
# 如果不配置,系统将以演示模式运行,数据不会持久化
# 获取配置: https://supabase.com/
# VITE_SUPABASE_URL=https://your-project.supabase.co
# VITE_SUPABASE_ANON_KEY=your-anon-key-here
# ==================== GitHub 集成配置 (可选) ====================
# 用于仓库分析功能
# 获取Token: https://github.com/settings/tokens
# VITE_GITHUB_TOKEN=your_github_token_here
# ==================== 应用配置 ====================
VITE_APP_ID=xcodereviewer
# ==================== 代码分析配置 ====================
VITE_MAX_ANALYZE_FILES=40
VITE_LLM_CONCURRENCY=2
VITE_LLM_GAP_MS=500