腾讯CodeBuddy AI IDE深度评测：从安装配置到实战技巧
CodeBuddy IDE是腾讯推出的AI集成开发环境，提供国内版和国际版双版本支持。国内版集成DeepSeek系列大模型并完全免费，国际版支持GPT-5、Gemini等模型并提供专业付费方案。本文基于v1.1.1版本详细介绍了IDE的核心功能、模型支持差异、价格策略，并分享了实用的全局配置规则和MCP工具自动执行配置方案，帮助开发者快速上手并优化开发 workflow。
CodeBuddy IDE是腾讯推出的一款AI IDE，分为国内版和国际版。CodeBuddy IDE实时融合了产品设计与开发，是一款一站式产品工作室，助你规划、开发和发布应用。到2025年10月26日，CodeBuddy IDE已经更新到v1.1.1，支持从MCP市场安装MCP应用，支持设置用户和项目规则，无论从界面美观度还是用户体验上，都上了一个大台阶。想了解国内其他IDE，可以点击访问 Trae IDE使用指南 和 Qoder IDE使用指南。
常用网站
官方网站（国内版）：https://copilot.tencent.com/ide/
官方网站（国际版）：https://www.codebuddy.ai/
国际版（测试版本）：Tencent Cloud Code Assistant CodeBuddy – AI Code Editor
使用文档（国内版）：https://copilot.tencent.com/docs/ide/What%20is%20our%20IDE%EF%BC%9F
使用文档（国际版）：https://copilot.tencent.com/docs/ide/What%20is%20our%20IDE%EF%BC%9F
支持的大模型
截至2025年10月26日，CodeBuddy IDE发布了v1.1.1版本。国内版主要支持国内的大模型，国际版支持国外的大模型。
国内版
1、Chat 模型支持DeepSeek-V3.1-Terminus、DeepSeek-V3-0324、DeepSeek-R1-0528、Hunyuan-Turbos 四个大模型。
2、Craft 模式支持 DeepSeek-V3.1-Terminus 和 DeepSeek-V3-0324 两个大模型，还新增加了一个Default模型，可以根据任务难度自动选择大模型。
国际版
国际版两个模式都支持GTP-5-Codex、GPT-5、GTP-5-mini、GPT-5-nano、GPT-4o-mini、Gemini-2.5-Flash、Gemini-2.5-Pro模型，还增加了一个Default模型，可以根据任务难度自动选择模型。
价格
国内版
完全免费
国际版
Pro版本9.95美元/月，一年119.40美元。
常用配置
全局规则
这是我在开发中用到的一些全局配置，仅供大家参考。
1. 请保持对话语言为中文
2. 我的系统为 Windows
3. 请自动修复代码中的 lint 错误
4. 只需完成我要求的功能，不要做多余的工作
5. 在 vue 文件中使用 defineProps 时，不需要从 vue 导入
6. 禁止使用 lint 命令
7. 当我让你参考某个文件时，请严格按照参考文件编写，例如：编程风格，用的数据库类型、配置
8. 当我让你根据实体类生成创建表的sql语句时，应该生成创建MySQL表的SQL语句，不需要添加索引和外键，不需要指定引擎和字符集，但是需要为表和字段添加注释
9. 当需要在vue文件中创建弹窗时，应该把弹窗放到单独的vue文件中
10. vue文件应全小写命名，单词之间用-分隔。
11. 当使用Diff edit工具失败时，不要重复调用，直接重写整个文件。内置模型
国际版
{
"code": 0,
"msg": "OK",
"requestId": "58514980ba2f40d18d07311e347e791e",
"data": {
"$schema": "product-schema.json",
"agents": [
{
"commands": [
"init",
"cr",
"tests",
"fix",
"explain",
"rules",
"summarize",
"help"
],
"description": "craft agent",
"instructions": "craft-agent-prompt",
"models": [
"default-model",
"gemini-3.0-flash",
"gemini-2.5-pro",
"gpt-5.2-codex",
"gpt-5.2",
"gpt-5.1",
"gpt-5.1-codex-max",
"auto-chat"
],
"name": "craft",
"optionalVariables": ["file", "git", "terminal", "agent", "rules"],
"tools": [
"read_file",
"list_files",
"search_file",
"search_content",
"semantic_search",
"RAG_search",
"execute_command",
"write_to_file",
"replace_in_file",
"delete_files",
"unit_test",
"plan_attempt_completion",
"mcp_server"
]
},
{
"commands": ["init", "cr", "explain", "summarize", "help"],
"description": "ask agent",
"instructions": "ask-agent-prompt",
"models": [
"default-model",
"gemini-3.0-flash",
"gemini-2.5-pro",
"gpt-5.2-codex",
"gpt-5.2",
"gpt-5.1",
"gpt-5.1-codex-max",
"auto-chat"
],
"name": "ask",
"optionalVariables": ["file", "git", "terminal", "agent", "rules"],
"tools": [
"read_file",
"list_files",
"search_file",
"search_content",
"semantic_search",
"RAG_search"
]
},
{
"commands": [
"init",
"cr",
"tests",
"fix",
"explain",
"rules",
"summarize",
"help"
],
"description": "plan agent",
"instructions": "plan-agent-prompt",
"models": [
"default-model",
"gemini-3.0-flash",
"gemini-2.5-pro",
"gpt-5.2-codex",
"gpt-5.2",
"gpt-5.1",
"gpt-5.1-codex-max"
],
"name": "plan",
"optionalVariables": ["file", "git", "terminal", "agent", "rules"],
"tools": [
"read_file",
"list_files",
"search_file",
"search_content",
"semantic_search",
"RAG_search",
"execute_command",
"write_to_file",
"replace_in_file",
"delete_files",
"unit_test",
"plan_attempt_completion",
"mcp_server"
]
},
{
"description": "agent",
"models": ["default-model", "gemini-2.5-pro", "auto-chat"],
"name": "agent"
},
{
"description": "chat",
"models": ["default-model", "gemini-2.5-pro", "auto-chat"],
"name": "chat"
},
{
"description": "enhance prompt",
"models": ["enhance-1.0"],
"name": "enhance prompt"
},
{
"description": "Inline chat ide for code editing",
"models": ["gpt-5.1"],
"name": "inline-chat"
},
{
"commands": ["terminal-chat"],
"description": "terminal chat ide",
"models": ["nes-1.2"],
"name": "terminal"
},
{
"description": "Code Completion agent",
"models": ["completion-1.0"],
"name": "CodeCompletion"
},
{
"description": "Code Completion agent for NES",
"instructions": "code-completion-nes-prompt",
"models": ["nes-1.2"],
"name": "CodeCompletionNes",
"variables": ["activeEditor", "workspaceFileDiffs", "diagnostics"]
},
{
"description": "Generate commit message",
"instructions": "commit-message-generate-prompt",
"models": ["nes-1.2"],
"name": "CommitMessage",
"variables": ["userInfo", "vcsDiffs", "vcsLogs", "systemInfo"]
},
{
"description": "Proxy To Remote Agent",
"models": ["nes-1.1"],
"name": "RemoteAgentProxy"
},
{ "description": "web-fetch", "models": ["o4-mini"], "name": "web-fetch" }
],
"authentication": {
"attributes": {
"platform": "ide",
"prefixPath": "/plugin",
"startChatAfterCompleted": true,
"storageKey": "planning-genie.new.accessToken",
"tokenHeader": "Authorization",
"tokenType": "bearerToken",
"usernameEncode": "URLEncode",
"usernameHeader": "X-User-Id"
},
"id": "Tencent-Cloud.genie-ide",
"label": "TencentCloud",
"type": "external-link-v2"
},
"commands": [
{
"description": "init is analyzing your codebase…",
"expand": "Please analyze this codebase and create a CODEBUDDY.md file, which will be given to future instances of Terminal Assistant Agent to operate in this repository.\n \nWhat to add:\n1. Commands that will be commonly used, such as how to build, lint, and run tests. Include the necessary commands to develop in this codebase, such as how to run a single test.\n2. High-level code architecture and structure so that future instances can be productive more quickly. Focus on the \"big picture\" architecture that requires reading multiple files to understand\n\nUsage notes:\n- First check if there's already an AGENTS.md file in the current directory. If it exists, DO NOT create a new CODEBUDDY.md file. Instead, suggest improvements to the existing AGENTS.md file.\n- If there's already a CODEBUDDY.md but no AGENTS.md, suggest improvements to the existing CODEBUDDY.md.\n- If there's already a AGENTS.md but no CODEBUDDY.md, suggest improvements to the existing AGENTS.md.\n- When creating a new file, create CODEBUDDY.md (not AGENTS.md) if neither exists.\n- When you make the initial file, do not repeat yourself and do not include obvious instructions like \"Provide helpful error messages to users\", \"Write unit tests for all new utilities\", \"Never include sensitive information (API keys, tokens) in code or commits\" \n- Avoid listing every component or file structure that can be easily discovered\n- Don't include generic development practices\n- If there are Claude Code rules (in ./CLAUDE.md) or Cursor rules (in .cursor/rules/ or .cursorrules) or Copilot rules (in .github/copilot-instructions.md) or ./AGENTS.md, make sure to include the important parts.\n- If there is a README.md, make sure to include the important parts. \n- Do not make up information such as \"Common Development Tasks\", \"Tips for Development\", \"Support and Documentation\" unless this is expressly included in other files that you read.\n- Be sure to prefix the file with the following text:\n```\n# CODEBUDDY.md This file provides guidance to CodeBuddy Code when working with code in this repository.\n```\n",
"name": "init",
"prompt": "init-prompt"
},
{
"description": "Code Review",
"expand": "Please refer to the provided reference information, and conduct a thorough code review, highlighting improvements, potential bugs, and optimizations based on your analysis.",
"name": "cr",
"prompt": "code-review-prompt"
},
{
"description": "Generate Unit Tests",
"expand": "Please refer to the provided reference information, and generate comprehensive unit tests to validate functionality, including edge cases, based on your understanding of the code.",
"name": "tests",
"prompt": "unit-test-prompt"
},
{
"description": "Explain how the selected code works",
"expand": "Please refer to the provided reference information, and clearly explain the code's logic, purpose, and key components in your own words.",
"name": "explain",
"prompt": "explain-prompt"
},
{
"description": "Propose a fix for the problems in the selected code",
"expand": "Please refer to the provided reference information to fix my code.",
"name": "fix",
"prompt": "fix-prompt"
},
{
"agent": "craft",
"description": "Generate documentation comments",
"name": "doc",
"prompt": "inline-chat-document-prompt"
},
{
"agent": "craft",
"name": "generate",
"prompt": "inline-chat-generate-prompt",
"stream": true,
"virtual": true
},
{
"agent": "craft",
"name": "edit",
"prompt": "inline-chat-edit-prompt",
"virtual": true
},
{
"description": "Terminal Chat in IDE",
"name": "terminal-chat",
"prompt": "terminal-command-generate-prompt"
},
{
"description": "Preview frontend project",
"expand": "Analyze and start preview service for frontend projects.",
"name": "preview",
"prompt": "preview-prompt"
},
{
"agent": "craft",
"description": "Generate Rules",
"name": "rules",
"prompt": "generate-rules",
"simple": true
},
{
"description": "Help for CodeBuddy IDE",
"expand": "/help",
"name": "help",
"prompt": "# CodeBuddy IDE Help Assistant\n\nYou are the CodeBuddy IDE help assistant, responsible for answering user questions about IDE usage.\n\n## Documentation Resources\n\n| Topic | Description | Documentation Link |\n|-------|-------------|-------------------|\n| Introduction | IDE introduction and overview | https://www.codebuddy.ai/docs/ide/Introduction |\n| Installation | How to install CodeBuddy IDE | https://www.codebuddy.ai/docs/ide/Getting-Started/Installation |\n| Quickstart | Getting started quickly | https://www.codebuddy.ai/docs/ide/Getting-Started/Quickstart |\n| Overview | User guide overview | https://www.codebuddy.ai/docs/ide/User-guide/Overview |\n| Code Completion | AI code completion feature | https://www.codebuddy.ai/docs/ide/User-guide/Completion |\n| Inline Chat | Inline chat feature | https://www.codebuddy.ai/docs/ide/User-guide/inline-chat |\n| Slash Commands | Available slash commands | https://www.codebuddy.ai/docs/ide/User-guide/Slash-Commands |\n| Context | Context configuration | https://www.codebuddy.ai/docs/ide/User-guide/Context |\n| Rules | Project rule configuration | https://www.codebuddy.ai/docs/ide/User-guide/Rules |\n| Checkpoint | Checkpoint feature | https://www.codebuddy.ai/docs/ide/User-guide/Checkpoint |\n| History | Conversation history | https://www.codebuddy.ai/docs/ide/User-guide/History |\n| Memory | Memory feature | https://www.codebuddy.ai/docs/ide/User-guide/Memory |\n| MCP | Model Context Protocol configuration | https://www.codebuddy.ai/docs/ide/User-guide/MCP |\n| Integration | Config integration services | https://www.codebuddy.ai/docs/ide/User-guide/Integration |\n| Preview | Frontend project preview | https://www.codebuddy.ai/docs/ide/User-guide/preview |\n| Deploy | Deploy projects to cloud | https://www.codebuddy.ai/docs/ide/User-guide/deploy |\n| Smart Commit | Smart commit feature | https://www.codebuddy.ai/docs/ide/User-guide/smart-commit |\n| Models | Available AI models | https://www.codebuddy.ai/docs/ide/Features/models |\n| Plan Mode | Plan mode feature | https://www.codebuddy.ai/docs/ide/Features/Plan-Mode |\n| Subagents | Subagents feature | https://www.codebuddy.ai/docs/ide/Features/Subagents |\n| Skills | Skills feature | https://www.codebuddy.ai/docs/ide/Features/Skills |\n| Hooks | Hooks feature | https://www.codebuddy.ai/docs/ide/Features/hooks |\n| Subscription | Subscription management | https://www.codebuddy.ai/docs/ide/Account/Subscription |\n| Pricing | Pricing plans | https://www.codebuddy.ai/docs/ide/Account/pricing |\n| Credits | Credits system | https://www.codebuddy.ai/docs/ide/Account/credits |\n| Usage | Usage statistics | https://www.codebuddy.ai/docs/ide/Account/usage |\n| Billing | Billing information | https://www.codebuddy.ai/docs/ide/Account/billing |\n| Invoice | Invoice management | https://www.codebuddy.ai/docs/ide/Account/invoice |\n| Best Practice | Best practices guide | https://www.codebuddy.ai/docs/ide/Best-practice/best-practice |\n| Troubleshooting | Common issues and solutions | https://www.codebuddy.ai/docs/ide/Support/Troubleshooting |\n| Security \u0026 Privacy | Security and privacy info | https://www.codebuddy.ai/docs/ide/Support/security-privacy |\n| Contact | Contact support | https://www.codebuddy.ai/docs/ide/Support/Contact |\n| Release Notes | Version update records | https://www.codebuddy.ai/docs/ide/release-notes/release-notes |\n\n## Response Strategy\n\n### Scenario 1: User has no specific question\nWhen the user just greets or requests help without a specific question, return the complete documentation navigation:\n\n```markdown\n# 👋 Welcome to CodeBuddy IDE Help Center!\n\nHere is the complete documentation, click links to view details:\n\n## 🚀 Getting Started\n- [Introduction](https://www.codebuddy.ai/docs/ide/Introduction)\n- [Installation](https://www.codebuddy.ai/docs/ide/Getting-Started/Installation)\n- [Quickstart](https://www.codebuddy.ai/docs/ide/Getting-Started/Quickstart)\n\n## 📖 User Guide\n- [Overview](https://www.codebuddy.ai/docs/ide/User-guide/Overview)\n- [Code Completion](https://www.codebuddy.ai/docs/ide/User-guide/Completion)\n- [Inline Chat](https://www.codebuddy.ai/docs/ide/User-guide/inline-chat)\n- [Slash Commands](https://www.codebuddy.ai/docs/ide/User-guide/Slash-Commands)\n- [Context](https://www.codebuddy.ai/docs/ide/User-guide/Context)\n- [Rules](https://www.codebuddy.ai/docs/ide/User-guide/Rules)\n- [Checkpoint](https://www.codebuddy.ai/docs/ide/User-guide/Checkpoint)\n- [History](https://www.codebuddy.ai/docs/ide/User-guide/History)\n- [Memory](https://www.codebuddy.ai/docs/ide/User-guide/Memory)\n- [MCP](https://www.codebuddy.ai/docs/ide/User-guide/MCP)\n- [Integration](https://www.codebuddy.ai/docs/ide/User-guide/Integration)\n- [Preview](https://www.codebuddy.ai/docs/ide/User-guide/preview)\n- [Deploy](https://www.codebuddy.ai/docs/ide/User-guide/deploy)\n- [Smart Commit](https://www.codebuddy.ai/docs/ide/User-guide/smart-commit)\n\n## ✨ Features\n- [Models](https://www.codebuddy.ai/docs/ide/Features/models)\n- [Plan Mode](https://www.codebuddy.ai/docs/ide/Features/Plan-Mode)\n- [Subagents](https://www.codebuddy.ai/docs/ide/Features/Subagents)\n- [Skills](https://www.codebuddy.ai/docs/ide/Features/Skills)\n- [Hooks](https://www.codebuddy.ai/docs/ide/Features/hooks)\n\n## 💳 Account\n- [Subscription](https://www.codebuddy.ai/docs/ide/Account/Subscription)\n- [Pricing](https://www.codebuddy.ai/docs/ide/Account/pricing)\n- [Credits](https://www.codebuddy.ai/docs/ide/Account/credits)\n- [Usage](https://www.codebuddy.ai/docs/ide/Account/usage)\n- [Billing](https://www.codebuddy.ai/docs/ide/Account/billing)\n- [Invoice](https://www.codebuddy.ai/docs/ide/Account/invoice)\n\n## 🏆 Best Practice\n- [Best Practice Guide](https://www.codebuddy.ai/docs/ide/Best-practice/best-practice)\n\n## ❓ Support\n- [Troubleshooting](https://www.codebuddy.ai/docs/ide/Support/Troubleshooting)\n- [Security \u0026 Privacy](https://www.codebuddy.ai/docs/ide/Support/security-privacy)\n- [Contact](https://www.codebuddy.ai/docs/ide/Support/Contact)\n\n## 📋 Release Notes\n- [Version Update Records](https://www.codebuddy.ai/docs/ide/release-notes/release-notes)\n\nFeel free to ask me specific questions!\n```\n\n### Scenario 2: User has specific questions\nMatch related topics based on user question keywords:\n\n| Keywords | Matched Topic |\n|----------|---------------|\n| install, setup, download | Installation |\n| start, begin, quickstart | Quickstart |\n| complete, completion, autocomplete, suggest | Code Completion |\n| inline, chat inline | Inline Chat |\n| slash, command, / | Slash Commands |\n| context, @, mention | Context |\n| rule, custom, configure behavior | Rules |\n| checkpoint, restore, snapshot | Checkpoint |\n| history, conversation, chat history | History |\n| memory, remember | Memory |\n| mcp, protocol | MCP |\n| integration, connect, service | Integration |\n| preview, view effect | Preview |\n| deploy, publish, release, launch | Deploy |\n| commit, smart commit, git message | Smart Commit |\n| model, ai model, switch model | Models |\n| plan, plan mode, planning | Plan Mode |\n| subagent, agent, sub agent | Subagents |\n| skill, skills | Skills |\n| hook, hooks, automation | Hooks |\n| subscription, subscribe, plan | Subscription |\n| price, pricing, cost | Pricing |\n| credit, credits, token | Credits |\n| usage, consumption | Usage |\n| billing, payment, pay | Billing |\n| invoice, receipt | Invoice |\n| best practice, recommend | Best Practice |\n| issue, error, not working, bug, problem | Troubleshooting |\n| security, privacy, data | Security \u0026 Privacy |\n| contact, support, help, feedback | Contact |\n| version, update, release | Release Notes |\n\n**Response Flow:**\n1. Identify the core topic of the user's question\n2. Provide the corresponding documentation link\n3. If the question is complex or the user needs detailed answers, use the `web_fetch` tool to get documentation content\n4. Provide specific, practical answers based on the documentation content\n\n### Scenario 3: Question is outside documentation scope\nIf the user's question is beyond the documentation coverage:\n1. Honestly inform that the question may not be in existing documentation\n2. Suggest checking [Troubleshooting](https://www.codebuddy.ai/docs/ide/Support/Troubleshooting) or [Introduction](https://www.codebuddy.ai/docs/ide/Introduction)\n3. Try to provide help based on general knowledge\n\n## Response Principles\n- 🎯 **Precise**: Directly provide the most relevant resources based on the question\n- 📝 **Concise**: Avoid redundant information, highlight key points\n- 🔗 **Actionable**: Always provide clickable documentation links\n- 🤝 **Friendly**: Maintain a friendly, professional tone\n\nNote: After your response, you must add the following sentence:\n✨ Feature guide unlocked! Also unlock your \"Code to Success\" red packet cover 🧧, [Click here to claim →](https://www.codebuddy.ai/promotion/?fromSource=gwzcw.10438475.10438475.10438475\u0026utm_medium=cpc\u0026utm_id=gwzcw.10438475.10438475.10438475)",
"tags": ["custom"]
}
],
"commitMessage": {},
"completion": {
"currentFileMaxLines": 200,
"maxInputCharacters": 10000,
"maxInputTokens": 4000,
"sensitivity": "medium",
"suffixPercent": 0.2
},
"config": {
"limitHint": "Your complimentary allowance has also been used up. To continue enjoying a seamless coding experience and all the exclusive benefits.",
"limitHintCN": "credit 额度已用完，立即升级订阅。"
},
"endpoint": "https://www.codebuddy.ai",
"featureToggles": {
"SupportHttpsAgentProxy": true,
"disabledTerminalCheck": true
},
"integrations": {
"builtins": {
"anydev": false,
"cloudStudio": true,
"eop": true,
"lighthouse": true,
"supabase": true,
"tcb": true
}
},
"knowledgeBases": [{ "provider": "Tencent" }],
"links": {
"craftShellHelpDocument": "https://cloud.tencent.com/document/product/1749/117896",
"helpDocument": "https://cloud.tencent.com/document/product/1749",
"helpLink": "https://www.codebuddy.ai/docs/ide/",
"issueFeedback": "https://cloud.tencent.com/online-service?from=intro_acc"
},
"log": { "output": 2 },
"models": [
{
"descriptionEn": "Enhanced model with improved performance for various tasks",
"descriptionZh": "性能增强的模型，适用于各种任务",
"id": "enhance-1.0",
"maxOutputTokens": 32000,
"name": "Enhance-1.0",
"supportsImages": false,
"supportsToolCall": true,
"vendor": "f"
},
{
"credits": "x2.20 credits",
"descriptionEn": "Excellent coding model, great for daily use",
"descriptionZh": "优秀的编码模型，适合日常使用",
"id": "default-model",
"isDefault": true,
"maxAllowedSize": 200000,
"maxInputTokens": 176000,
"maxOutputTokens": 24000,
"name": "Default",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1,
"vendor": "e"
},
{
"credits": "x1.33 credits",
"descriptionEn": "OpenAI’s flagship model, excelling at long-horizon tasks",
"descriptionZh": "OpenAI 旗舰模型，擅长长程任务",
"id": "gpt-5.2-codex",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5.2-Codex",
"onlyReasoning": true,
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": true,
"supportsReasoning": true,
"supportsToolCall": true,
"vendor": "e"
},
{
"credits": "x1.33 credits",
"descriptionEn": "OpenAI's coding-specialized model, great for complex coding",
"descriptionZh": "OpenAI 代码专用模型，非常擅长处理复杂的编码任务",
"id": "gpt-5.2",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5.2",
"onlyReasoning": true,
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": false,
"supportsReasoning": true,
"supportsToolCall": true,
"vendor": "e"
},
{
"credits": "x0.95 credits",
"descriptionEn": "OpenAI's flagship model, good for planning, debugging, coding, and more",
"descriptionZh": "OpenAI 旗舰模型，适合规划、调试、编码等任务",
"id": "gpt-5.1",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5.1",
"onlyReasoning": true,
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": true,
"supportsReasoning": true,
"supportsToolCall": true,
"vendor": "e"
},
{
"credits": "x0.95 credits",
"descriptionEn": "OpenAI's latest model specifically for coding, good for ambitious coding tasks",
"descriptionZh": "OpenAI 最新的编码专用模型，适合大型、有挑战性的编码任务",
"id": "gpt-5.1-codex",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5.1-Codex",
"onlyReasoning": true,
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": true,
"supportsReasoning": true,
"supportsToolCall": true,
"vendor": "e"
},
{
"credits": "x0.95 credits",
"descriptionEn": "OpenAI's coding-specialized model, great for complex coding",
"descriptionZh": "OpenAI 代码专用模型，非常擅长处理复杂的编码任务",
"id": "gpt-5.1-codex-max",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5.1-Codex-Max",
"onlyReasoning": true,
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": true,
"supportsReasoning": true,
"supportsToolCall": true,
"vendor": "e"
},
{
"credits": "x0.19 credits",
"descriptionEn": "Similar to GPT-5.1 Codex, but smaller and cheaper",
"descriptionZh": "与 GPT-5.1 Codex 类似，但更小、更便宜",
"id": "gpt-5.1-codex-mini",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5.1-Codex-Mini",
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": true,
"supportsReasoning": true,
"supportsToolCall": true,
"vendor": "e"
},
{
"credits": "x0.95 credits",
"descriptionEn": "OpenAI's flagship model, good for planning, debugging, coding, and more",
"descriptionZh": "OpenAI 的旗舰模型，适合规划、调试、编码等任务",
"id": "gpt-5",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 0.6,
"vendor": "e"
},
{
"credits": "x0.95 credits",
"descriptionEn": "OpenAI's model specifically for coding",
"descriptionZh": "OpenAI 专为编码设计的模型",
"id": "gpt-5-codex",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5-Codex",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 0.6,
"vendor": "e"
},
{
"credits": "x0.19 credits",
"descriptionEn": "Smaller and faster version of GPT-5, suitable for everyday tasks with lower cost",
"descriptionZh": "GPT-5 的小型版本，更快、更便宜，适用于日常任务",
"id": "gpt-5-mini",
"maxAllowedSize": 272000,
"maxInputTokens": 272000,
"maxOutputTokens": 72000,
"name": "GPT-5-mini",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 0.6,
"vendor": "e"
},
{
"credits": "x0.04 credits",
"descriptionEn": "Ultra-lightweight GPT-5 variant optimized for speed and minimal cost",
"descriptionZh": "超轻量版 GPT-5，针对极低成本与高速度进行了优化",
"id": "gpt-5-nano",
"maxAllowedSize": 200000,
"maxInputTokens": 200000,
"maxOutputTokens": 72000,
"name": "GPT-5-nano",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 0.6,
"vendor": "e"
},
{
"credits": "x0.92 credits",
"descriptionEn": "Smaller, faster GPT model for everyday coding and general tasks",
"descriptionZh": "更小、更快的 GPT 模型，适用于日常编码和通用任务",
"id": "o4-mini",
"maxAllowedSize": 128000,
"maxInputTokens": 104000,
"maxOutputTokens": 24000,
"name": "GPT-4o-mini",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 0.6,
"vendor": "e"
},
{
"descriptionEn": "General-purpose chat model for conversational tasks",
"descriptionZh": "适用于对话任务的通用聊天模型",
"id": "chat-1.0",
"maxOutputTokens": 32000,
"name": "chat-1.0",
"supportsImages": false,
"supportsToolCall": true,
"vendor": "f"
},
{
"descriptionEn": "Lightweight completion model for quick text generation",
"descriptionZh": "用于快速文本生成的轻量级补全模型",
"id": "completion-1.0",
"maxOutputTokens": 256,
"name": "completion-1.0",
"supportsExtra": true,
"vendor": "j"
},
{
"descriptionEn": "Updated completion model with improved performance",
"descriptionZh": "性能改进的升级版补全模型",
"id": "completion-1.2",
"maxOutputTokens": 256,
"name": "completion-1.2",
"supportsExtra": true,
"vendor": "j"
},
{
"descriptionEn": "Compact model for efficient processing",
"descriptionZh": "用于高效处理的紧凑型模型",
"id": "nes-1.0",
"maxOutputTokens": 256,
"name": "nes-1.0",
"vendor": "f"
},
{
"descriptionEn": "Enhanced version with increased output capacity",
"descriptionZh": "输出容量增强的升级版本",
"id": "nes-1.1",
"maxOutputTokens": 8192,
"name": "nes-1.1",
"vendor": "f"
},
{
"credits": "x0.33 credits",
"descriptionEn": "Google's fast preview model with multimodal capabilities",
"descriptionZh": "Google 的快速预览模型，支持多模态能力",
"id": "gemini-3.0-flash",
"maxAllowedSize": 200000,
"maxInputTokens": 200000,
"maxOutputTokens": 32000,
"name": "Gemini-3.0-Flash",
"onlyReasoning": true,
"reasoning": { "effort": "medium", "summary": "auto" },
"supportsImages": true,
"supportsReasoning": true,
"supportsToolCall": true,
"temperature": 1,
"vendor": "i"
},
{
"credits": "x0.31 credits",
"descriptionEn": "Fast and efficient Gemini model designed for quick responses and lightweight tasks",
"descriptionZh": "高效快速的 Gemini 模型，适合即时响应与轻量任务",
"id": "gemini-2.5-flash",
"maxAllowedSize": 200000,
"maxInputTokens": 200000,
"maxOutputTokens": 32000,
"name": "Gemini-2.5-Flash",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1
},
{
"credits": "x1.30 credits",
"descriptionEn": "Large refactors, navigation/search and problem solving, 200k context window",
"descriptionZh": "适用于大型重构、导航/搜索和问题求解",
"id": "gemini-2.5-pro",
"maxAllowedSize": 200000,
"maxInputTokens": 200000,
"maxOutputTokens": 64000,
"name": "Gemini-2.5-Pro",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1
},
{
"credits": "x0.57 credits",
"descriptionEn": "Intelligent auto-selection model that adapts to different tasks",
"descriptionZh": "智能自动选择模型，适应不同任务需求",
"disabledMultimodal": true,
"id": "auto-chat",
"maxInputTokens": 168000,
"maxOutputTokens": 32000,
"name": "Auto",
"supportsImages": false,
"supportsToolCall": true,
"temperature": 1,
"vendor": "f"
},
{
"credits": "x0.57 credits",
"descriptionEn": "Automatic model selection for optimal performance",
"descriptionZh": "自动模型选择，实现最佳性能",
"disabledMultimodal": true,
"id": "nes-1.2",
"maxInputTokens": 32000,
"maxOutputTokens": 8192,
"name": "auto",
"supportsImages": false,
"supportsToolCall": true,
"temperature": 0.8,
"vendor": "f"
}
],
"platform": "CodeBuddyIDE",
"productFeatures": {
"CRLFCompatible": true,
"Codebase": false,
"CompletionsPrefetching": true,
"CompletionsRelatedSnippets": true,
"CompletionsResultFusion": true,
"CursorPositonPrefetching": true,
"InlineChat": false,
"InlineCompletions": true,
"Mock": true,
"MultiFileWithPromptParam": true,
"MultiFileWithSeparateParams": false,
"MultiStepCompletions": true,
"NesCompletions": false,
"NesCompletionsPrefetching": true,
"NesRangeFix": true,
"NesRepeatFilter": true,
"RemoveBelowExist": true,
"StatusBar": false,
"SummaryWebFetch": true,
"TrimByIndentation": true,
"WebBrowserFetch": true,
"WebFetch": true
},
"productName": "",
"requestMaxStepLimit": 500,
"stagingEndpoint": "https://staging-codebuddy.tencent.com",
"telemetry": {
"report": {
"model": { "enabled": true },
"standard": { "enabled": true }
},
"tracing": { "enabled": true }
},
"tools": [
{
"description": "Run a natural language search for relevant code or documentation comments from the user's current workspace. Returns relevant code snippets from the user's current workspace if it is large, or the full contents of the workspace if it is small.",
"name": "semantic_search"
}
],
"updates": { "disabled": true }
}
}
国内版
自定义模型
国内模型
创建文件：C:\Users\liteng\.codebuddy\models.json，添加下面的内容可以添加GLM-4.7和MiniMax-M2.1模型。
{
"models": [
{
"id": "glm-4.7",
"name": "GLM-4.7",
"vendor": "OpenAI",
"apiKey": "your-actual-api-key",
"maxInputTokens": 200000,
"maxOutputTokens": 48000,
"url": "https://open.bigmodel.cn/api/paas/v4/chat/completions",
"supportsImages": false,
"supportsReasoning": true,
"supportsToolCall": true,
"temperature": 1
},
{
"id": "MiniMax-M2.1",
"name": "MiniMax-M2.1",
"vendor": "OpenAI",
"apiKey": "your-actual-api-key",
"maxInputTokens": 128000,
"maxOutputTokens": 8192,
"url": "https://minimax-m2.com/api/v1/chat/completions",
"supportsImages": false,
"supportsReasoning": true,
"supportsToolCall": true,
"temperature": 1
}
]
}
使用代理
{
"models": [
{
"id": "claude-sonnet-4.5",
"name": "sonnet-4.5",
"descriptionEn": "Excellent coding model, great for daily use",
"descriptionZh": "优秀的编码模型，适合日常使用",
"vendor": "e",
"apiKey": "",
"maxAllowedSize": 200000,
"maxInputTokens": 176000,
"maxOutputTokens": 24000,
"url": "http://127.0.0.1:8081/v1/chat/completions",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1
},
{
"id": "claude-opus-4.5",
"name": "opus-4.5",
"descriptionEn": "Excellent coding model, great for daily use",
"descriptionZh": "优秀的编码模型，适合日常使用",
"vendor": "e",
"apiKey": "",
"maxAllowedSize": 200000,
"maxInputTokens": 176000,
"maxOutputTokens": 24000,
"url": "http://127.0.0.1:8081/v1/chat/completions",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1
},
{
"id": "claude-haiku-4.5",
"name": "haiku-4.5",
"descriptionEn": "Excellent coding model, great for daily use",
"descriptionZh": "优秀的编码模型，适合日常使用",
"vendor": "e",
"apiKey": "",
"maxAllowedSize": 200000,
"maxInputTokens": 176000,
"maxOutputTokens": 24000,
"url": "http://127.0.0.1:8081/v1/chat/completions",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1
},
{
"id": "claude-sonnet-4",
"name": "sonnet-4",
"descriptionEn": "Excellent coding model, great for daily use",
"descriptionZh": "优秀的编码模型，适合日常使用",
"vendor": "e",
"apiKey": "",
"maxAllowedSize": 200000,
"maxInputTokens": 176000,
"maxOutputTokens": 24000,
"url": "http://127.0.0.1:8081/v1/chat/completions",
"supportsImages": true,
"supportsToolCall": true,
"temperature": 1
}
]
}
MCP配置
默认每个MCP工具都需要手工确认，很麻烦，这里我提供一个常用MCP配置文件，可以自动执行所有MCP工具。
{
"mcpServers": {
"context7": {
"command": "npx",
"args": ["-y", "@upstash/context7-mcp@latest"],
"env": {
"DEFAULT_MINIMUM_TOKENS": "10000"
},
"disabled": false,
"autoApprove": ["resolve-library-id", "get-library-docs"]
},
"playwright": {
"command": "npx",
"args": ["-y", "@executeautomation/playwright-mcp-server"],
"disabled": false,
"autoApprove": [
"playwright_navigate",
"playwright_screenshot",
"playwright_click",
"playwright_iframe_click",
"playwright_iframe_fill",
"playwright_fill",
"playwright_select",
"playwright_hover",
"playwright_upload_file",
"playwright_evaluate",
"playwright_console_logs",
"playwright_close",
"playwright_get",
"playwright_post",
"playwright_put",
"playwright_patch",
"playwright_delete",
"playwright_expect_response",
"playwright_assert_response",
"playwright_custom_user_agent",
"playwright_get_visible_text",
"playwright_get_visible_html",
"playwright_go_back",
"playwright_go_forward",
"playwright_drag",
"playwright_press_key",
"playwright_save_as_pdf",
"playwright_click_and_switch_tab",
"start_codegen_session",
"end_codegen_session",
"get_codegen_session",
"clear_codegen_session"
]
},
"Sequential Thinking": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],
"env": {},
"disabled": false,
"autoApprove": ["sequentialthinking"]
}
}
}
最后更新于2月前
本文由人工编写，AI优化，转载请注明原文地址： 腾讯CodeBuddy IDE官方网站
推荐阅读
评论 (3)
请 登录 后发表评论
微笑天使2025-11-16 11:38:47感谢分享，CodeBuddy IDE的功能介绍很全面！想了解国内版和国际版在价格和团队协作功能上具体有哪些差异？
管理员2025-11-16 21:16:32国内版是免费的，国际版需要购买会员。由于国内版和国际版模型不一样，在编程能力上，国际版强得多。
赵小迈Mike2025-11-08 16:32:55感谢分享！文档里关于国内版和国际版模型支持的对比很清晰，帮我快速确定了该用哪个版本。