github copilot problem

[ahmedrageh]

=== REQUEST INFO ===
Version: 6.6.22
URL: /v1/chat/completions
Method: POST
Timestamp: 2025-12-17T13:18:32.8195707+03:00

=== HEADERS ===
User-Agent: oai-compatible-copilot/0.1.8 VSCode/1.107.0
Authorization: Bearer 12...56
Accept-Language: *
Accept-Encoding: gzip, deflate
Connection: keep-alive
Content-Type: application/json
Sec-Fetch-Mode: cors
Accept: /
Content-Length: 111817

=== API RESPONSE ===
{
"error": {
"code": 400,
"message": "{"type":"error","error":{"type":"invalid_request_error","message":"messages.3.content.0.tool_use.id: String should match pattern '^[a-zA-Z0-9_-]+$'"},"request_id":"req_vrtx_011CWC66JdZ4zEgoGsShm311"}",
"status": "INVALID_ARGUMENT"
}
}

=== RESPONSE ===
Status: 400
Access-Control-Allow-Origin: *
Access-Control-Allow-Methods: GET, POST, PUT, PATCH, DELETE, OPTIONS
Access-Control-Allow-Headers: *
Content-Type: application/json
Cache-Control: no-cache
Connection: keep-alive

{
"error": {
"code": 400,
"message": "{"type":"error","error":{"type":"invalid_request_error","message":"messages.3.content.0.tool_use.id: String should match pattern '^[a-zA-Z0-9_-]+$'"},"request_id":"req_vrtx_011CWC66JdZ4zEgoGsShm311"}",
"status": "INVALID_ARGUMENT"
}
}

[ahmedrageh]

=== REQUEST INFO ===
Version: 6.6.22
URL: /v1/chat/completions
Method: POST
Timestamp: 2025-12-17T13:18:32.8195707+03:00

=== HEADERS ===
User-Agent: oai-compatible-copilot/0.1.8 VSCode/1.107.0
Authorization: Bearer 12...56
Accept-Language: *
Accept-Encoding: gzip, deflate
Connection: keep-alive
Content-Type: application/json
Sec-Fetch-Mode: cors
Accept: /
Content-Length: 111817

=== REQUEST BODY ===
{"model":"gemini-claude-sonnet-4-5","messages":[{"role":"system","content":"You are an expert AI programming assistant, working with a user in the VS Code editor.\nWhen asked for your name, you must respond with "GitHub Copilot". When asked about the model you are using, you must state that you are using gemini-claude-sonnet-4-5 via gemini.\nFollow the user's requirements carefully & to the letter.\nFollow Microsoft content policies.\nAvoid content that violates copyrights.\nIf you are asked to generate content that is harmful, hateful, racist, sexist, lewd, or violent, only respond with "Sorry, I can't assist with that."\nKeep your answers short and impersonal.\n\nYou are a highly sophisticated automated coding agent with expert-level knowledge across many different programming languages and frameworks.\nThe user will ask a question, or ask you to perform a task, and it may require lots of research to answer correctly. There is a selection of tools that let you perform actions or retrieve helpful context to answer the user's question.\nYou will be given some context and attachments along with the user prompt. You can use them if they are relevant to the task, and ignore them if not. Some attachments may be summarized with omitted sections like /* Lines 123-456 omitted */. You can use the read_file tool to read more context if needed. Never pass this omitted line marker to an edit tool.\nIf you can infer the project type (languages, frameworks, and libraries) from the user's query or the context that you have, make sure to keep them in mind when making changes.\nIf the user wants you to implement a feature and they have not specified the files to edit, first break down the user's request into smaller concepts and think about the kinds of files you need to grasp each concept.\nIf you aren't sure which tool is relevant, you can call multiple tools. You can call tools repeatedly to take actions or gather as much context as needed until you have completed the task fully. Don't give up unless you are sure the request cannot be fulfilled with the tools you have. It's YOUR RESPONSIBILITY to make sure that you have done all you can to collect necessary context.\nWhen reading files, prefer reading large meaningful chunks rather than consecutive small sections to minimize tool calls and gain better context.\nDon't make assumptions about the situation- gather context first, then perform the task or answer the question.\nThink creatively and explore the workspace in order to make a complete fix.\nDon't repeat yourself after a tool call, pick up where you left off.\nNEVER print out a codeblock with file changes unless the user asked for it. Use the appropriate edit tool instead.\nNEVER print out a codeblock with a terminal command to run unless the user asked for it. Use the run_in_terminal tool instead.\nYou don't need to read a file if it's already provided in context.\n\n\nIf the user is requesting a code sample, you can answer it directly without using any tools.\nWhen using a tool, follow the JSON schema very carefully and make sure to include ALL required properties.\nNo need to ask permission before using a tool.\nNEVER say the name of a tool to a user. For example, instead of saying that you'll use the run_in_terminal tool, say "I'll run the command in a terminal".\nIf you think running multiple tools can answer the user's question, prefer calling them in parallel whenever possible, but do not call semantic_search in parallel.\nWhen using the read_file tool, prefer reading a large section over calling the read_file tool many times in sequence. You can also think of all the pieces you may be interested in and read them in parallel. Read large enough context to ensure you get what you need.\nIf semantic_search returns the full contents of the text files in the workspace, you have all the workspace context.\nYou can use the grep_search to get an overview of a file by searching for a string within that one file, instead of using read_file many times.\nIf you don't know exactly the string or filename pattern you're looking for, use semantic_search to do a semantic search across the workspace.\nDon't call the run_in_terminal tool multiple times in parallel. Instead, run one command and wait for the output before running the next command.\nWhen invoking a tool that takes a file path, always use the absolute file path. If the file has a scheme like untitled: or vscode-userdata:, then use a URI with the scheme.\nNEVER try to edit a file by running terminal commands unless the user specifically asks for it.\nTools can be disabled by the user. You may see tools used previously in the conversation that are not currently available. Be careful to only use the tools that are currently available to you.\n\n<instruction forToolsWithPrefix="mcp_io">\nThe GitHub MCP Server provides tools to interact with GitHub platform.\n\nTool selection guidance:\n\t1. Use 'list_' tools for broad, simple retrieval and pagination of all items of a type (e.g., all issues, all PRs, all branches) with basic filtering.\n\t2. Use 'search_' tools for targeted queries with specific criteria, keywords, or complex filters (e.g., issues with certain text, PRs by author, code containing functions).\n\nContext management:\n\t1. Use pagination whenever possible with batches of 5-10 items.\n\t2. Use minimal_output parameter set to true if the full information is not needed to accomplish a task.\n\nTool usage guidance:\n\t1. For 'search_' tools: Use separate 'sort' and 'order' parameters if available for sorting results - do not include 'sort:' syntax in query strings. Query strings should contain only search criteria (e.g., 'org:google language:python'), not sorting instructions. Always call 'get_me' first to understand current user permissions and context. ## Issues\n\nCheck 'list_issue_types' first for organizations to use proper issue types. Use 'search_issues' before creating new issues to avoid duplicates. Always set 'state_reason' when closing issues. ## Pull Requests\n\nPR review workflow: Always use 'pull_request_review_write' with method 'create' to create a pending review, then 'add_comment_to_pending_review' to add comments, and finally 'pull_request_review_write' with method 'submit_pending' to submit the review for complex reviews with line-specific comments.\n\nBefore creating a pull request, search for pull request templates in the repository. Template files are called pull_request_template.md or they're located in '.github/PULL_REQUEST_TEMPLATE' directory. Use the template content to structure the PR description and then call create_pull_request tool.\n\nHere are common scenarios you may encounter, followed by a description of the steps to follow and the tools to use. Match these to user requests:\nIf the user is bootstrapping a new project, you MUST always follow this workflow:\n- STEP 1: Set up a repository for the project unless one has already been set up by the user.\n- STEP 2: If a repository for the project exists, use issues tools to create at least one tracking issue for the project.\nWhen the user requests to search for issues in a repository using natural language, use the semantic_issues_search tool over search_issues.\n\n\nTo edit notebook files in the workspace, you can use the edit_notebook_file tool.\nUse the run_notebook_cell tool instead of executing Jupyter related commands in the Terminal, such as jupyter notebook, jupyter lab, install jupyter or the like.\nUse the copilot_getNotebookSummary tool to get the summary of the notebook (this includes the list or all cells along with the Cell Id, Cell type and Cell Language, execution details and mime types of the outputs, if any).\nImportant Reminder: Avoid referencing Notebook Cell Ids in user messages. Use cell number instead.\nImportant Reminder: Markdown cells cannot be executed\n\n\nUse proper Markdown formatting in your answers. When referring to a filename or symbol in the user's workspace, wrap it in backticks.\n\nThe class Person is in src/models/person.ts.\nThe function calculateTotal is defined in lib/utils/math.ts.\nYou can find the configuration in config/app.config.json.\n\nUse KaTeX for math equations in your answers.\nWrap inline math equations in $.\nWrap more complex blocks of math equations in $$.\n\n\n\n\n\nHere is a list of agents that can be used when running a subagent.\nEach agent has optionally a description with the agent's purpose and expertise. When asked to run a subagent, choose the most appropriate agent from this list.\nUse the 'runSubagent' tool with the agent name to run the subagent.\n\nPlan\nResearches and outlines multi-step plans\nOutline the goal or problem to research\n\n\n\n\n\n"},{"role":"user","content":"<environment_info>\nThe user's current OS is: Windows\n</environment_info>\n<workspace_info>\nI am working in a workspace with the following folders:\n- d:\mcp\Antigravity2api-main \nI am working in a workspace that has the following structure:\n\nAPI.md\nconfig.json\ndocker-compose.yml\nDockerfile\nLICENSE\npackage.json\nQUOTA_FEATURE.md\nREADME.md\nTOKEN_API.md\nclient/\n\teslint.config.js\n\tindex.html\n\tpackage.json\n\tpostcss.config.js\n\tREADME.md\n\ttailwind.config.js\n\tvite.config.js\n\tpublic/\n\tsrc/\n\t\tApp.css\n\t\tApp.jsx\n\t\tindex.css\n\t\tmain.jsx\n\t\tassets/\n\t\tcomponents/\n\t\t\tAuthOverlay.jsx\n\t\t\tCodeBlock.jsx\n\t\t\tErrorBoundary.jsx\n\t\t\tLayout.jsx\n\t\tcontext/\n\t\t\tAuthContext.jsx\n\t\tlib/\n\t\t\tutils.js\n\t\tpages/\n\t\t\tDashboard.jsx\n\t\t\tDocs.jsx\n\t\t\tKeys.jsx\n\t\t\tLogs.jsx\n\t\t\tMonitor.jsx\n\t\t\tSettings.jsx\n\t\t\tTest.jsx\n\t\t\tTokens.jsx\ndata/\n\taccounts.json\n\taccounts000.json\n\tapp_logs.json\n\tquotas.json\npublic/\n\tapp.js\n\tindex.html\n\tstyle.css\n\tassets/\n\t\tindex-BEs7JOvM.js\n\t\tindex-DOSSKk6s.css\n\timages/\nscripts/\n\toauth-server.js\n\trefresh-tokens.js\nsrc/\n\tAntigravityRequester.js\n\tadmin/\n\t\tkey_manager.js\n\t\tlog_manager.js\n\t\tmonitor.js\n\t\troutes.js\n\t\tsession.js\n\t\tsettings_manager.js\n\t\ttoken_admin.js\n\tapi/\n\t\tclient.js\n\tauth/\n\t\tjwt.js\n\t\tquota_manager.js\n\t\ttoken_manager.js\n\tbin/\n\t\tantigravity_requester_android_arm64\n\t\tantigravity_requester_linux_amd64\n\tconfig/\n\t\tconfig.js\n\t\tinit-env.js\n\tconstants/\n\t\toauth.js\n\troutes/\n\t\tadmin.js\n\t\tsd.js\n\tserver/\n\t\tindex.js\n\tutils/\n\t\tconfigReloader.js\n\t\tdeepMerge.js\n\t\tenvParser.js\n\t\tidGenerator.js\n\t\tidle_manager.js\n\t\timageStorage.js\n\t\tlogger.js\n\t\tmemoryManager.js\n\t\tutils.js\ntest/\n\ttest-get-ip.js\n\ttest-image-generation.js\n\ttest-memory.js\n\ttest-request.js\n\ttest-token-rotation.js\n\ttest-transform.js\nuploads/\n\nThis is the state of the context at this point in the conversation. The view of the workspace structure may be truncated. You can use tools to collect more context if needed.\n</workspace_info>\n"},{"role":"user","content":"\nThe current date is December 17, 2025.\nTerminals:\nTerminal: powershell\nTerminal: powershell\nLast Command: node test/test-transform.js\nCwd: D:\mcp\Antigravity2api-main\nExit Code: 0\n\n\n\nWhen using the replace_string_in_file tool, include 3-5 lines of unchanged code before and after the string you want to replace, to make it unambiguous which part of the file should be edited.\nFor maximum efficiency, whenever you plan to perform multiple independent edit operations, invoke them simultaneously using multi_replace_string_in_file tool rather than sequentially. This will greatly improve user's cost and time efficiency leading to a better user experience. Do not announce which tool you're using (for example, avoid saying "I'll implement all the changes using multi_replace_string_in_file").\n\n\n\nاهلا\n\n"},{"role":"assistant","content":"أهلاً وسهلاً! 👋\n\nأنا GitHub Copilot، كيف يمكنني مساعدتك اليوم؟\n\nأرى أنك تعمل على مشروع Antigravity2api وهو يبدو كـ API مع واجهة مستخدم React. المشروع يحتوي على:\n\n- Backend: خادم Node.js مع إدارة المفاتيح والتوكنات\n- Frontend: تطبيق React مع Vite و Tailwind CSS\n- Docker: دعم للتشغيل عبر الحاويات\n\nهل تحتاج مساعدة في شيء محدد؟"},{"role":"user","content":"\nThe current date is December 17, 2025.\nTerminals:\nTerminal: powershell\nTerminal: powershell\nLast Command: node test/test-transform.js\nCwd: D:\mcp\Antigravity2api-main\nExit Code: 0\n\n\n\nWhen using the replace_string_in_file tool, include 3-5 lines of unchanged code before and after the string you want to replace, to make it unambiguous which part of the file should be edited.\nFor maximum efficiency, whenever you plan to perform multiple independent edit operations, invoke them simultaneously using multi_replace_string_in_file tool rather than sequentially. This will greatly improve user's cost and time efficiency leading to a better user experience. Do not announce which tool you're using (for example, avoid saying "I'll implement all the changes using multi_replace_string_in_file").\n\n\n\nقم بتحليل كامل المشروع الحالي \n\n"},{"role":"assistant","tool_calls":[{"id":"toolu_vrtx_01BxSTBwzftcFSpGg641nkrU::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","type":"function","function":{"name":"read_file","arguments":"{"endLine":100,"filePath":"d:\\mcp\\Antigravity2api-main\\README.md","startLine":1}"}},{"id":"toolu_vrtx_01F5SYVgR8HkSQ51zXBxzDur::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","type":"function","function":{"name":"read_file","arguments":"{"startLine":1,"endLine":60,"filePath":"d:\\mcp\\Antigravity2api-main\\package.json"}"}},{"id":"toolu_vrtx_01QGd1pQy41UDPbHVtkgZbB5::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","type":"function","function":{"name":"read_file","arguments":"{"startLine":1,"endLine":150,"filePath":"d:\\mcp\\Antigravity2api-main\\API.md"}"}},{"id":"toolu_vrtx_01KT9jNbVNTQBhoQscksEiME::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","type":"function","function":{"name":"read_file","arguments":"{"filePath":"d:\\mcp\\Antigravity2api-main\\config.json","startLine":1,"endLine":100}"}}]},{"role":"tool","tool_call_id":"toolu_vrtx_01BxSTBwzftcFSpGg641nkrU::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","content":"File: d:\\mcp\\Antigravity2api-main\\README.md. Lines 1 to 100 (631 lines total): \nmarkdown\n# Antigravity to OpenAI API 代理服务\n\n将 Google Antigravity API 转换为 OpenAI 兼容格式的代理服务，支持流式响应、工具调用和多账号管理。\n\n## 功能特性\n\n- ✅ OpenAI API 兼容格式\n- ✅ 流式和非流式响应\n- ✅ 工具调用（Function Calling）支持\n- ✅ 多账号自动轮换（支持多种轮询策略）\n- ✅ Token 自动刷新\n- ✅ API Key 认证\n- ✅ 思维链（Thinking）输出，兼容 OpenAI reasoning_effort 参数和 DeepSeek reasoning_content 格式\n- ✅ 图片输入支持（Base64 编码）\n- ✅ 图片生成支持（gemini-3-pro-image 模型）\n- ✅ Pro 账号随机 ProjectId 支持\n- ✅ 模型额度查看（实时显示剩余额度和重置时间）\n- ✅ SD WebUI API 兼容（支持 txt2img/img2img）\n- ✅ 心跳机制（防止 Cloudflare 超时断连）\n- ✅ 模型列表缓存（减少 API 请求）\n- ✅ 资格校验自动回退（无资格时自动生成随机 ProjectId）\n- ✅ 真 System 消息合并（开头连续多条 system 与 SystemInstruction 合并）\n- ✅ 隐私模式（自动隐藏敏感信息）\n- ✅ 内存优化（从 8+ 进程减少为 2 个进程，内存占用从 100MB+ 降为 50MB+）\n- ✅ 对象池复用（减少 50%+ 临时对象创建，降低 GC 频率）\n\n## 环境要求\n\n- Node.js >= 18.0.0\n\n## 快速开始\n\n### 1. 安装依赖\n\n```bash\nnpm install\n```\n\n### 2. 配置环境变量\n\n复制 `.env.example` 为 `.env` 并编辑配置：\n\n```bash\ncp .env.example .env\n```\n\n编辑 `.env` 文件配置必要参数：\n\n```env\n# 必填配置\nAPI_KEY=sk-text\nADMIN_USERNAME=admin\nADMIN_PASSWORD=admin123\nJWT_SECRET=your-jwt-secret-key-change-this-in-production\n\n# 可选配置\n# PROXY=http://127.0.0.1:7890\n# SYSTEM_INSTRUCTION=你是聊天机器人\n# IMAGE_BASE_URL=http://your-domain.com\n```\n\n### 3. 登录获取 Token\n\n```bash\nnpm run login\n```\n\n浏览器会自动打开 Google 授权页面，授权后 Token 会保存到 `data/accounts.json`。\n\n### 4. 启动服务\n\n```bash\nnpm start\n```\n\n服务将在 `http://localhost:8045` 启动。\n\n## Docker 部署\n\n### 使用 Docker Compose（推荐）\n\n1. **配置环境变量**\n\n创建 `.env` 文件：\n\n```bash\ncp .env.example .env\n```\n\n编辑 `.env` 文件配置必要参数。\n\n2. **启动服务**\n\n```bash\ndocker-compose up -d\n```\n\n3. **查看日志**\n\n```bash\n"},{"role":"tool","tool_call_id":"toolu_vrtx_01F5SYVgR8HkSQ51zXBxzDur::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","content":"json\n{\n \"name\": \"antigravity-to-openai\",\n \"version\": \"1.0.0\",\n \"description\": \"Antigravity API 转 OpenAI 格式的代理服务\",\n \"type\": \"module\",\n \"main\": \"src/server/index.js\",\n \"scripts\": {\n \"start\": \"node --expose-gc src/server/index.js\",\n \"start:no-gc\": \"node src/server/index.js\",\n \"login\": \"node scripts/oauth-server.js\",\n \"refresh\": \"node scripts/refresh-tokens.js\",\n \"dev\": \"node --expose-gc --watch src/server/index.js\"\n },\n \"keywords\": [\n \"antigravity\",\n \"openai\",\n \"api\",\n \"proxy\"\n ],\n \"author\": \"\",\n \"license\": \"MIT\",\n \"dependencies\": {\n \"axios\": \"^1.13.2\",\n \"cors\": \"^2.8.5\",\n \"dotenv\": \"^17.2.3\",\n \"express\": \"^5.2.1\",\n \"jsonwebtoken\": \"^9.0.3\"\n },\n \"engines\": {\n \"node\": \">=18.0.0\"\n }\n}\n\n"},{"role":"tool","tool_call_id":"toolu_vrtx_01QGd1pQy41UDPbHVtkgZbB5::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","content":"File: d:\\mcp\\Antigravity2api-main\\API.md. Lines 1 to 150 (501 lines total): \nmarkdown\n# API 使用文档\n\n本文档介绍如何使用 Antigravity2API 提供的 OpenAI 兼容 API。\n\n## 基础配置\n\n所有 API 请求需要在 Header 中携带 API Key：\n\n```\nAuthorization: Bearer YOUR_API_KEY\n```\n\n默认服务地址：`http://localhost:8045`\n\n## 目录\n\n- [获取模型列表](#获取模型列表)\n- [聊天补全](#聊天补全)\n- [工具调用](#工具调用function-calling)\n- [图片输入](#图片输入多模态)\n- [图片生成](#图片生成)\n- [思维链模型](#思维链模型)\n- [SD WebUI 兼容 API](#sd-webui-兼容-api)\n- [管理 API](#管理-api)\n- [使用示例](#使用示例)\n\n## 获取模型列表\n\n```bash\ncurl http://localhost:8045/v1/models \\\n -H \"Authorization: Bearer sk-text\"\n```\n\n**说明**：模型列表会缓存 1 小时（可通过 `config.json` 的 `cache.modelListTTL` 配置），减少 API 请求。\n\n## 聊天补全\n\n### 流式响应\n\n```bash\ncurl http://localhost:8045/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer sk-text\" \\\n -d '{\n \"model\": \"gemini-2.0-flash-exp\",\n \"messages\": [{\"role\": \"user\", \"content\": \"你好\"}],\n \"stream\": true\n }'\n```\n\n### 非流式响应\n\n```bash\ncurl http://localhost:8045/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer sk-text\" \\\n -d '{\n \"model\": \"gemini-2.0-flash-exp\",\n \"messages\": [{\"role\": \"user\", \"content\": \"你好\"}],\n \"stream\": false\n }'\n```\n\n## 工具调用（Function Calling）\n\n```bash\ncurl http://localhost:8045/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer sk-text\" \\\n -d '{\n \"model\": \"gemini-2.0-flash-exp\",\n \"messages\": [{\"role\": \"user\", \"content\": \"北京天气怎么样\"}],\n \"tools\": [{\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_weather\",\n \"description\": \"获取天气信息\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\"type\": \"string\", \"description\": \"城市名称\"}\n },\n \"required\": [\"location\"]\n }\n }\n }]\n }'\n```\n\n## 图片输入（多模态）\n\n支持 Base64 编码的图片输入，兼容 OpenAI 的多模态格式：\n\n```bash\ncurl http://localhost:8045/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer sk-text\" \\\n -d '{\n \"model\": \"gemini-2.0-flash-exp\",\n \"messages\": [{\n \"role\": \"user\",\n \"content\": [\n {\"type\": \"text\", \"text\": \"这张图片里有什么？\"},\n {\n \"type\": \"image_url\",\n \"image_url\": {\n \"url\": \"data:image/jpeg;base64,/9j/4AAQSkZJRg...\"\n }\n }\n ]\n }],\n \"stream\": true\n }'\n```\n\n### 支持的图片格式\n\n- JPEG/JPG (`data:image/jpeg;base64,...`)\n- PNG (`data:image/png;base64,...`)\n- GIF (`data:image/gif;base64,...`)\n- WebP (`data:image/webp;base64,...`)\n\n## 图片生成\n\n支持使用 `gemini-3-pro-image` 模型生成图片，生成的图片会以 Markdown 格式返回：\n\n```bash\ncurl http://localhost:8045/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer sk-text\" \\\n -d '{\n \"model\": \"gemini-3-pro-image\",\n \"messages\": [{\"role\": \"user\", \"content\": \"画一只可爱的猫\"}],\n \"stream\": false\n }'\n```\n\n**响应示例**：\n```json\n{\n \"choices\": [{\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"![image](http://localhost:8045/images/abc123.png)\"\n }\n }]\n}\n```\n\n**注意**：\n"},{"role":"tool","tool_call_id":"toolu_vrtx_01KT9jNbVNTQBhoQscksEiME::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","content":"json\n{\n \"server\": {\n \"port\": 8045,\n \"host\": \"0.0.0.0\",\n \"maxRequestSize\": \"500mb\",\n \"heartbeatInterval\": 15000,\n \"memoryThreshold\": 25\n },\n \"rotation\": {\n \"strategy\": \"round_robin\",\n \"requestCount\": 50\n },\n \"api\": {\n \"url\": \"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:streamGenerateContent?alt=sse\",\n \"modelsUrl\": \"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:fetchAvailableModels\",\n \"noStreamUrl\": \"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:generateContent\",\n \"host\": \"daily-cloudcode-pa.sandbox.googleapis.com\",\n \"userAgent\": \"antigravity/1.11.3 windows/amd64\"\n },\n \"defaults\": {\n \"temperature\": 1,\n \"topP\": 1,\n \"topK\": 50,\n \"maxTokens\": 32000,\n \"thinkingBudget\": 16000\n },\n \"cache\": {\n \"modelListTTL\": 3600000\n },\n \"other\": {\n \"timeout\": 300000,\n \"skipProjectIdFetch\": false,\n \"useNativeAxios\": false\n }\n}\n"},{"role":"assistant","tool_calls":[{"id":"toolu_vrtx_01JexGLkACMphw6HpAp4pKr1","type":"function","function":{"name":"read_file","arguments":"{"endLine":150,"filePath":"d:\\mcp\\Antigravity2api-main\\src\\server\\index.js","startLine":1}"}},{"id":"toolu_vrtx_01MBoTAxssAYF92Lpe9WPV6i","type":"function","function":{"name":"read_file","arguments":"{"filePath":"d:\\mcp\\Antigravity2api-main\\src\\auth\\token_manager.js","startLine":1,"endLine":100}"}},{"id":"toolu_vrtx_01CsBzJvtHUVT8wSUEnzc9Th","type":"function","function":{"name":"read_file","arguments":"{"endLine":100,"filePath":"d:\\mcp\\Antigravity2api-main\\src\\AntigravityRequester.js","startLine":1}"}},{"id":"toolu_vrtx_01JGhV1MYpTuGX4whDEtaBDM","type":"function","function":{"name":"read_file","arguments":"{"filePath":"d:\\mcp\\Antigravity2api-main\\client\\package.json","startLine":1,"endLine":50}"}}]},{"role":"tool","tool_call_id":"toolu_vrtx_01JexGLkACMphw6HpAp4pKr1","content":"File: d:\\mcp\\Antigravity2api-main\\src\\server\\index.js. Lines 1 to 150 (361 lines total): \njavascript\nimport express from 'express';\nimport cors from 'cors';\nimport path from 'path';\nimport { fileURLToPath } from 'url';\nimport { generateAssistantResponse, generateAssistantResponseNoStream, getAvailableModels, generateImageForSD, closeRequester } from '../api/client.js';\nimport { generateRequestBody } from '../utils/utils.js';\nimport logger from '../utils/logger.js';\nimport config from '../config/config.js';\nimport tokenManager from '../auth/token_manager.js';\nimport adminRouter from '../routes/admin.js';\nimport sdRouter from '../routes/sd.js';\nimport memoryManager, { MemoryPressure } from '../utils/memoryManager.js';\n\nconst __filename = fileURLToPath(import.meta.url);\nconst __dirname = path.dirname(__filename);\n\nconst app = express();\n\n// ==================== 心跳机制（防止 CF 超时） ====================\nconst HEARTBEAT_INTERVAL = config.server.heartbeatInterval || 15000; // 从配置读取心跳间隔\nconst SSE_HEARTBEAT = Buffer.from(': heartbeat\\n\\n');\n\n// 创建心跳定时器\nconst createHeartbeat = (res) => {\n const timer = setInterval(() => {\n if (!res.writableEnded) {\n res.write(SSE_HEARTBEAT);\n } else {\n clearInterval(timer);\n }\n }, HEARTBEAT_INTERVAL);\n \n // 响应结束时清理\n res.on('close', () => clearInterval(timer));\n res.on('finish', () => clearInterval(timer));\n \n return timer;\n};\n\n// 预编译的常量字符串（避免重复创建）\nconst SSE_PREFIX = Buffer.from('data: ');\nconst SSE_SUFFIX = Buffer.from('\\n\\n');\nconst SSE_DONE = Buffer.from('data: [DONE]\\n\\n');\n\n// 工具函数：生成响应元数据\nconst createResponseMeta = () => ({\n id: `chatcmpl-${Date.now()}`,\n created: Math.floor(Date.now() / 1000)\n});\n\n// 工具函数：设置流式响应头\nconst setStreamHeaders = (res) => {\n res.setHeader('Content-Type', 'text/event-stream');\n res.setHeader('Cache-Control', 'no-cache');\n res.setHeader('Connection', 'keep-alive');\n res.setHeader('X-Accel-Buffering', 'no'); // 禁用 nginx 缓冲\n};\n\n// 工具函数：构建流式数据块（使用动态对象池减少 GC）\n// 支持 DeepSeek 格式的 reasoning_content\nconst chunkPool = [];\nconst getChunkObject = () => chunkPool.pop() || { choices: [{ index: 0, delta: {}, finish_reason: null }] };\nconst releaseChunkObject = (obj) => {\n const maxSize = memoryManager.getPoolSizes().chunk;\n if (chunkPool.length < maxSize) chunkPool.push(obj);\n};\n\n// 注册内存清理回调\nmemoryManager.registerCleanup((pressure) => {\n const poolSizes = memoryManager.getPoolSizes();\n // 根据压力缩减对象池\n while (chunkPool.length > poolSizes.chunk) {\n chunkPool.pop();\n }\n});\n\n// 启动内存管理器\nmemoryManager.start(30000);\n\nconst createStreamChunk = (id, created, model, delta, finish_reason = null) => {\n const chunk = getChunkObject();\n chunk.id = id;\n chunk.object = 'chat.completion.chunk';\n chunk.created = created;\n chunk.model = model;\n chunk.choices[0].delta = delta;\n chunk.choices[0].finish_reason = finish_reason;\n return chunk;\n};\n\n// 工具函数：零拷贝写入流式数据\nconst writeStreamData = (res, data) => {\n const json = JSON.stringify(data);\n // 释放对象回池\n if (data.choices) releaseChunkObject(data);\n res.write(SSE_PREFIX);\n res.write(json);\n res.write(SSE_SUFFIX);\n};\n\n// 工具函数：结束流式响应\nconst endStream = (res) => {\n res.write(SSE_DONE);\n res.end();\n};\n\napp.use(cors());\napp.use(express.json({ limit: config.security.maxRequestSize }));\n\n// 静态文件服务\napp.use('/images', express.static(path.join(__dirname, '../../public/images')));\napp.use(express.static(path.join(__dirname, '../../public')));\n\n// 管理路由\napp.use('/admin', adminRouter);\n\napp.use((err, req, res, next) => {\n if (err.type === 'entity.too.large') {\n return res.status(413).json({ error: `请求体过大，最大支持 ${config.security.maxRequestSize}` });\n }\n next(err);\n});\n\napp.use((req, res, next) => {\n const ignorePaths = ['/images', '/favicon.ico', '/.well-known', '/sdapi/v1/options', '/sdapi/v1/samplers', '/sdapi/v1/schedulers', '/sdapi/v1/upscalers', '/sdapi/v1/latent-upscale-modes', '/sdapi/v1/sd-vae', '/sdapi/v1/sd-modules'];\n if (!ignorePaths.some(path => req.path.startsWith(path))) {\n const start = Date.now();\n res.on('finish', () => {\n logger.request(req.method, req.path, res.statusCode, Date.now() - start);\n });\n }\n next();\n});\napp.use('/sdapi/v1', sdRouter);\n\napp.use((req, res, next) => {\n if (req.path.startsWith('/v1/')) {\n const apiKey = config.security?.apiKey;\n if (apiKey) {\n const authHeader = req.headers.authorization;\n const providedKey = authHeader?.startsWith('Bearer ') ? authHeader.slice(7) : authHeader;\n if (providedKey !== apiKey) {\n logger.warn(`API Key 验证失败: ${req.method} ${req.path}`);\n return res.status(401).json({ error: 'Invalid API Key' });\n }\n }\n }\n next();\n});\n\n"},{"role":"tool","tool_call_id":"toolu_vrtx_01MBoTAxssAYF92Lpe9WPV6i","content":"File: d:\\mcp\\Antigravity2api-main\\src\\auth\\token_manager.js. Lines 1 to 100 (477 lines total): \njavascript\nimport fs from 'fs';\nimport path from 'path';\nimport { fileURLToPath } from 'url';\nimport axios from 'axios';\nimport { log } from '../utils/logger.js';\nimport { generateSessionId, generateProjectId } from '../utils/idGenerator.js';\nimport config, { getConfigJson } from '../config/config.js';\nimport { OAUTH_CONFIG } from '../constants/oauth.js';\n\nconst __filename = fileURLToPath(import.meta.url);\nconst __dirname = path.dirname(__filename);\n\n// 轮询策略枚举\nconst RotationStrategy = {\n ROUND_ROBIN: 'round_robin', // 均衡负载：每次请求切换\n QUOTA_EXHAUSTED: 'quota_exhausted', // 额度耗尽才切换\n REQUEST_COUNT: 'request_count' // 自定义次数后切换\n};\n\nclass TokenManager {\n constructor(filePath = path.join(__dirname,'..','..','data' ,'accounts.json')) {\n this.filePath = filePath;\n this.tokens = [];\n this.currentIndex = 0;\n \n // 轮询策略相关 - 使用原子操作避免锁\n this.rotationStrategy = RotationStrategy.ROUND_ROBIN;\n this.requestCountPerToken = 50; // request_count 策略下每个token请求次数后切换\n this.tokenRequestCounts = new Map(); // 记录每个token的请求次数\n \n this.ensureFileExists();\n this.initialize();\n }\n\n ensureFileExists() {\n const dir = path.dirname(this.filePath);\n if (!fs.existsSync(dir)) {\n fs.mkdirSync(dir, { recursive: true });\n }\n if (!fs.existsSync(this.filePath)) {\n fs.writeFileSync(this.filePath, '[]', 'utf8');\n log.info('✓ 已创建账号配置文件');\n }\n }\n\n async initialize() {\n try {\n log.info('正在初始化token管理器...');\n const data = fs.readFileSync(this.filePath, 'utf8');\n let tokenArray = JSON.parse(data);\n \n this.tokens = tokenArray.filter(token => token.enable !== false).map(token => ({\n ...token,\n sessionId: generateSessionId()\n }));\n \n this.currentIndex = 0;\n this.tokenRequestCounts.clear();\n \n // 加载轮询策略配置\n this.loadRotationConfig();\n \n if (this.tokens.length === 0) {\n log.warn('⚠ 暂无可用账号，请使用以下方式添加：');\n log.warn(' 方式1: 运行 npm run login 命令登录');\n log.warn(' 方式2: 访问前端管理页面添加账号');\n } else {\n log.info(`成功加载 ${this.tokens.length} 个可用token`);\n if (this.rotationStrategy === RotationStrategy.REQUEST_COUNT) {\n log.info(`轮询策略: ${this.rotationStrategy}, 每token请求 ${this.requestCountPerToken} 次后切换`);\n } else {\n log.info(`轮询策略: ${this.rotationStrategy}`);\n }\n }\n } catch (error) {\n log.error('初始化token失败:', error.message);\n this.tokens = [];\n }\n }\n\n // 加载轮询策略配置\n loadRotationConfig() {\n try {\n const jsonConfig = getConfigJson();\n if (jsonConfig.rotation) {\n this.rotationStrategy = jsonConfig.rotation.strategy || RotationStrategy.ROUND_ROBIN;\n this.requestCountPerToken = jsonConfig.rotation.requestCount || 10;\n }\n } catch (error) {\n log.warn('加载轮询配置失败，使用默认值:', error.message);\n }\n }\n\n // 更新轮询策略（热更新）\n updateRotationConfig(strategy, requestCount) {\n if (strategy && Object.values(RotationStrategy).includes(strategy)) {\n this.rotationStrategy = strategy;\n }\n if (requestCount && requestCount > 0) {\n this.requestCountPerToken = requestCount;\n"},{"role":"tool","tool_call_id":"toolu_vrtx_01CsBzJvtHUVT8wSUEnzc9Th","content":"File: d:\\mcp\\Antigravity2api-main\\src\\AntigravityRequester.js. Lines 1 to 100 (363 lines total): \njavascript\nimport { spawn } from 'child_process';\nimport os from 'os';\nimport path from 'path';\nimport { fileURLToPath } from 'url';\nimport fs from 'fs';\n\nconst __dirname = path.dirname(fileURLToPath(import.meta.url));\n\n// 缓冲区大小警告阈值（不限制，只警告）\nconst BUFFER_WARNING_SIZE = 50 * 1024 * 1024; // 50MB 警告\n\nclass antigravityRequester {\n constructor(options = {}) {\n this.binPath = options.binPath;\n this.executablePath = options.executablePath || this._getExecutablePath();\n this.proc = null;\n this.requestId = 0;\n this.pendingRequests = new Map();\n this.buffer = '';\n this.writeQueue = Promise.resolve();\n this.bufferWarned = false;\n }\n\n _getExecutablePath() {\n const platform = os.platform();\n const arch = os.arch();\n \n let filename;\n if (platform === 'win32') {\n filename = 'antigravity_requester_windows_amd64.exe';\n } else if (platform === 'android') {\n filename = 'antigravity_requester_android_arm64';\n } else if (platform === 'linux') {\n filename = 'antigravity_requester_linux_amd64';\n } else {\n throw new Error(`Unsupported platform: ${platform}`);\n }\n \n const binPath = this.binPath || path.join(__dirname, 'bin');\n const requester_execPath = path.join(binPath, filename);\n // 设置执行权限（非Windows平台）\n if (platform !== 'win32') {\n try {\n fs.chmodSync(requester_execPath, 0o755);\n } catch (error) {\n console.warn(`Could not set executable permissions: ${error.message}`);\n }\n }\n return requester_execPath;\n }\n\n _ensureProcess() {\n if (this.proc) return;\n\n this.proc = spawn(this.executablePath, [], {\n stdio: ['pipe', 'pipe', 'pipe']\n });\n\n // 设置 stdin 为非阻塞模式\n if (this.proc.stdin.setDefaultEncoding) {\n this.proc.stdin.setDefaultEncoding('utf8');\n }\n\n // 增大 stdout 缓冲区以减少背压\n if (this.proc.stdout.setEncoding) {\n this.proc.stdout.setEncoding('utf8');\n }\n \n // 使用 setImmediate 异步处理数据,避免阻塞\n this.proc.stdout.on('data', (data) => {\n const chunk = data.toString();\n \n // 缓冲区大小监控（仅警告，不限制，因为图片响应可能很大）\n if (!this.bufferWarned && this.buffer.length > BUFFER_WARNING_SIZE) {\n console.warn(`AntigravityRequester: 缓冲区较大 (${Math.round(this.buffer.length / 1024 / 1024)}MB)，可能有大型响应`);\n this.bufferWarned = true;\n }\n \n this.buffer += chunk;\n \n // 使用 setImmediate 异步处理,避免阻塞 stdout 读取\n setImmediate(() => {\n let start = 0;\n let end;\n \n // 高效的行分割（避免 split 创建大量字符串）\n while ((end = this.buffer.indexOf('\\n', start)) !== -1) {\n const line = this.buffer.slice(start, end).trim();\n start = end + 1;\n \n if (!line) continue;\n \n try {\n const response = JSON.parse(line);\n const pending = this.pendingRequests.get(response.id);\n if (!pending) continue;\n\n if (pending.streamResponse) {\n pending.streamResponse._handleChunk(response);\n if (response.type === 'end' || response.type === 'error') {\n"},{"role":"tool","tool_call_id":"toolu_vrtx_01JGhV1MYpTuGX4whDEtaBDM","content":"json\n{\n \"name\": \"client\",\n \"private\": true,\n \"version\": \"0.0.0\",\n \"type\": \"module\",\n \"scripts\": {\n \"dev\": \"vite\",\n \"build\": \"vite build\",\n \"lint\": \"eslint .\",\n \"preview\": \"vite preview\"\n },\n \"dependencies\": {\n \"antigravity-to-openai\": \"file:..\",\n \"clsx\": \"^2.1.1\",\n \"framer-motion\": \"^12.23.24\",\n \"lucide-react\": \"^0.554.0\",\n \"react\": \"^19.2.0\",\n \"react-dom\": \"^19.2.0\",\n \"react-router-dom\": \"^7.9.6\",\n \"tailwind-merge\": \"^3.4.0\"\n },\n \"devDependencies\": {\n \"@eslint/js\": \"^9.39.1\",\n \"@tailwindcss/postcss\": \"^4.1.17\",\n \"@types/react\": \"^19.2.5\",\n \"@types/react-dom\": \"^19.2.3\",\n \"@vitejs/plugin-react\": \"^5.1.1\",\n \"autoprefixer\": \"^10.4.22\",\n \"eslint\": \"^9.39.1\",\n \"eslint-plugin-react-hooks\": \"^7.0.1\",\n \"eslint-plugin-react-refresh\": \"^0.4.24\",\n \"globals\": \"^16.5.0\",\n \"postcss\": \"^8.5.6\",\n \"tailwindcss\": \"^4.1.17\",\n \"vite\": \"npm:[email protected]\"\n },\n \"overrides\": {\n \"vite\": \"npm:[email protected]\"\n }\n}\n\n"}],"stream":true,"stream_options":{"include_usage":true},"temperature":0,"top_p":1,"tools":[{"type":"function","function":{"name":"create_directory","description":"Create a new directory structure in the workspace. Will recursively create all directories in the path, like mkdir -p. You do not need to use this tool before using create_file, that tool will automatically create the needed directories.","parameters":{"type":"object","properties":{"dirPath":{"type":"string","description":"The absolute path to the directory to create."}},"required":["dirPath"]}}},{"type":"function","function":{"name":"create_file","description":"This is a tool for creating a new file in the workspace. The file will be created with the specified content. The directory will be created if it does not already exist. Never use this tool to edit a file that already exists.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to create."},"content":{"type":"string","description":"The content to write to the file."}},"required":["filePath","content"]}}},{"type":"function","function":{"name":"create_new_jupyter_notebook","description":"Generates a new Jupyter Notebook (.ipynb) in VS Code. Jupyter Notebooks are interactive documents commonly used for data exploration, analysis, visualization, and combining code with narrative text. Prefer creating plain Python files or similar unless a user explicitly requests creating a new Jupyter Notebook or already has a Jupyter Notebook opened or exists in the workspace.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to use to generate the jupyter notebook. This should be a clear and concise description of the notebook the user wants to create."}},"required":["query"]}}},{"type":"function","function":{"name":"create_new_workspace","description":"Get comprehensive setup steps to help the user create complete project structures in a VS Code workspace. This tool is designed for full project initialization and scaffolding, not for creating individual files.\n\nWhen to use this tool:\n- User wants to create a new complete project from scratch\n- Setting up entire project frameworks (TypeScript projects, React apps, Node.js servers, etc.)\n- Initializing Model Context Protocol (MCP) servers with full structure\n- Creating VS Code extensions with proper scaffolding\n- Setting up Next.js, Vite, or other framework-based projects\n- User asks for "new project", "create a workspace", "set up a [framework] project"\n- Need to establish complete development environment with dependencies, config files, and folder structure\n\nWhen NOT to use this tool:\n- Creating single files or small code snippets\n- Adding individual files to existing projects\n- Making modifications to existing codebases\n- User asks to "create a file" or "add a component"\n- Simple code examples or demonstrations\n- Debugging or fixing existing code\n\nThis tool provides complete project setup including:\n- Folder structure creation\n- Package.json and dependency management\n- Configuration files (tsconfig, eslint, etc.)\n- Initial boilerplate code\n- Development environment setup\n- Build and run instructions\n\nUse other file creation tools for individual files within existing projects.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to use to generate the new workspace. This should be a clear and concise description of the workspace the user wants to create."}},"required":["query"]}}},{"type":"function","function":{"name":"edit_notebook_file","description":"This is a tool for editing an existing Notebook file in the workspace. Generate the "explanation" property first.\nThe system is very smart and can understand how to apply your edits to the notebooks.\nWhen updating the content of an existing cell, ensure newCode preserves whitespace and indentation exactly and does NOT include any code markers such as (...existing code...).","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file to edit, or the URI of a untitled, not yet named, file, such as untitled:Untitled-1."},"cellId":{"type":"string","description":"Id of the cell that needs to be deleted or edited. Use the value TOP, BOTTOMwhen inserting a cell at the top or bottom of the notebook, else provide the id of the cell after which a new cell is to be inserted. Remember, if a cellId is provided and editType=insert, then a cell will be inserted after the cell with the provided cellId."},"newCode":{"anyOf":[{"type":"string","description":"The code for the new or existing cell to be edited. Code should not be wrapped within <VSCode.Cell> tags. Do NOT include code markers such as (...existing code...) to indicate existing code."},{"type":"array","items":{"type":"string","description":"The code for the new or existing cell to be edited. Code should not be wrapped within <VSCode.Cell> tags"}}]},"language":{"type":"string","description":"The language of the cell.markdown, python, javascript, julia, etc."},"editType":{"type":"string","enum":["insert","delete","edit"],"description":"The operation peformed on the cell, whether insert, deleteoredit.\nUse the editTypefield to specify the operation:insertto add a new cell,editto modify an existing cell's content, anddeleteto remove a cell."}},"required":["filePath","editType","cellId"]}}},{"type":"function","function":{"name":"fetch_webpage","description":"Fetches the main content from a web page. This tool is useful for summarizing or analyzing the content of a webpage. You should use this tool when you think the user is looking for information from a specific webpage.","parameters":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"An array of URLs to fetch content from."},"query":{"type":"string","description":"The query to search for in the web page's content. This should be a clear and concise description of the content you want to find."}},"required":["urls","query"]}}},{"type":"function","function":{"name":"file_search","description":"Search for files in the workspace by glob pattern. This only returns the paths of matching files. Use this tool when you know the exact filename pattern of the files you're searching for. Glob patterns match from the root of the workspace folder. Examples:\n- **/*.{js,ts} to match all js/ts files in the workspace.\n- src/** to match all files under the top-level src folder.\n- **/foo/**/*.js to match all js files under any foo folder in the workspace.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"Search for files with names or paths matching this glob pattern."},"maxResults":{"type":"number","description":"The maximum number of results to return. Do not use this unless necessary, it can slow things down. By default, only some matches are returned. If you use this and don't see what you're looking for, you can try again with a more specific query or a larger maxResults."}},"required":["query"]}}},{"type":"function","function":{"name":"grep_search","description":"Do a fast text search in the workspace. Use this tool when you want to search with an exact string or regex. If you are not sure what words will appear in the workspace, prefer using regex patterns with alternation (|) or character classes to search for multiple potential words at once instead of making separate searches. For example, use 'function|method|procedure' to look for all of those words at once. Use includePattern to search within files matching a specific pattern, or in a specific file, using a relative path. Use 'includeIgnoredFiles' to include files normally ignored by .gitignore, other ignore files, andfiles.excludeandsearch.excludesettings. Warning: using this may cause the search to be slower, only set it when you want to search in ignored folders like node_modules or build outputs. Use this tool when you want to see an overview of a particular file, instead of using read_file many times to look for code within a file.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The pattern to search for in files in the workspace. Use regex with alternation (e.g., 'word1|word2|word3') or character classes to find multiple potential words in a single search. Be sure to set the isRegexp property properly to declare whether it's a regex or plain text pattern. Is case-insensitive."},"isRegexp":{"type":"boolean","description":"Whether the pattern is a regex."},"includePattern":{"type":"string","description":"Search files matching this glob pattern. Will be applied to the relative path of files within the workspace. To search recursively inside a folder, use a proper glob pattern like \"src/folder/**\". Do not use | in includePattern."},"maxResults":{"type":"number","description":"The maximum number of results to return. Do not use this unless necessary, it can slow things down. By default, only some matches are returned. If you use this and don't see what you're looking for, you can try again with a more specific query or a larger maxResults."},"includeIgnoredFiles":{"type":"boolean","description":"Whether to include files that would normally be ignored according to .gitignore, other ignore files andfiles.excludeandsearch.excludesettings. Warning: using this may cause the search to be slower. Only set it when you want to search in ignored folders like node_modules or build outputs."}},"required":["query","isRegexp"]}}},{"type":"function","function":{"name":"get_changed_files","description":"Get git diffs of current file changes in a git repository. Don't forget that you can use run_in_terminal to run git commands in a terminal as well.","parameters":{"type":"object","properties":{"repositoryPath":{"type":"string","description":"The absolute path to the git repository to look for changes in. If not provided, the active git repository will be used."},"sourceControlState":{"type":"array","items":{"type":"string","enum":["staged","unstaged","merge-conflicts"]},"description":"The kinds of git state to filter by. Allowed values are: 'staged', 'unstaged', and 'merge-conflicts'. If not provided, all states will be included."}}}}},{"type":"function","function":{"name":"get_errors","description":"Get any compile or lint errors in a specific file or across all files. If the user mentions errors or problems in a file, they may be referring to these. Use the tool to see the same errors that the user is seeing. If the user asks you to analyze all errors, or does not specify a file, use this tool to gather errors for all files. Also use this tool after editing a file to validate the change.","parameters":{"type":"object","properties":{"filePaths":{"description":"The absolute paths to the files or folders to check for errors. Omit 'filePaths' when retrieving all errors.","type":"array","items":{"type":"string"}}}}}},{"type":"function","function":{"name":"copilot_getNotebookSummary","description":"This is a tool returns the list of the Notebook cells along with the id, cell types, line ranges, language, execution information and output mime types for each cell. This is useful to get Cell Ids when executing a notebook or determine what cells have been executed and what order, or what cells have outputs. If required to read contents of a cell use this to determine the line range of a cells, and then use read_file tool to read a specific line range. Requery this tool if the contents of the notebook change.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file with the cell to run, or the URI of a untitled, not yet named, file, such asuntitled:Untitled-1.ipynb"}},"required":["filePath"]}}},{"type":"function","function":{"name":"get_project_setup_info","description":"Do not call this tool without first calling the tool to create a workspace. This tool provides a project setup information for a Visual Studio Code workspace based on a project type and programming language.","parameters":{"type":"object","properties":{"projectType":{"type":"string","description":"The type of project to create. Supported values are: 'python-script', 'python-project', 'mcp-server', 'model-context-protocol-server', 'vscode-extension', 'next-js', 'vite' and 'other'"}},"required":["projectType"]}}},{"type":"function","function":{"name":"get_search_view_results","description":"The results from the search view","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"get_vscode_api","description":"Get comprehensive VS Code API documentation and references for extension development. This tool provides authoritative documentation for VS Code's extensive API surface, including proposed APIs, contribution points, and best practices. Use this tool for understanding complex VS Code API interactions.\n\nWhen to use this tool:\n- User asks about specific VS Code APIs, interfaces, or extension capabilities\n- Need documentation for VS Code extension contribution points (commands, views, settings, etc.)\n- Questions about proposed APIs and their usage patterns\n- Understanding VS Code extension lifecycle, activation events, and packaging\n- Best practices for VS Code extension development architecture\n- API examples and code patterns for extension features\n- Troubleshooting extension-specific issues or API limitations\n\nWhen NOT to use this tool:\n- Creating simple standalone files or scripts unrelated to VS Code extensions\n- General programming questions not specific to VS Code extension development\n- Questions about using VS Code as an editor (user-facing features)\n- Non-extension related development tasks\n- File creation or editing that doesn't involve VS Code extension APIs\n\nCRITICAL usage guidelines:\n1. Always include specific API names, interfaces, or concepts in your query\n2. Mention the extension feature you're trying to implement\n3. Include context about proposed vs stable APIs when relevant\n4. Reference specific contribution points when asking about extension manifest\n5. Be specific about the VS Code version or API version when known\n\nScope: This tool is for EXTENSION DEVELOPMENT ONLY - building tools that extend VS Code itself, not for general file creation or non-extension programming tasks.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to search vscode documentation for. Should contain all relevant context."}},"required":["query"]}}},{"type":"function","function":{"name":"github_repo","description":"Searches a GitHub repository for relevant source code snippets. Only use this tool if the user is very clearly asking for code snippets from a specific GitHub repository. Do not use this tool for Github repos that the user has open in their workspace.","parameters":{"type":"object","properties":{"repo":{"type":"string","description":"The name of the Github repository to search for code in. Should must be formatted as '/'."},"query":{"type":"string","description":"The query to search for repo. Should contain all relevant context."}},"required":["repo","query"]}}},{"type":"function","function":{"name":"install_extension","description":"Install an extension in VS Code. Use this tool to install an extension in Visual Studio Code as part of a new workspace creation process only.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The ID of the extension to install. This should be in the format .."},"name":{"type":"string","description":"The name of the extension to install. This should be a clear and concise description of the extension."}},"required":["id","name"]}}},{"type":"function","function":{"name":"list_code_usages","description":"Request to list all usages (references, definitions, implementations etc) of a function, class, method, variable etc. Use this tool when \n1. Looking for a sample implementation of an interface or class\n2. Checking how a function is used throughout the codebase.\n3. Including and updating all usages when changing a function, method, or constructor","parameters":{"type":"object","properties":{"symbolName":{"type":"string","description":"The name of the symbol, such as a function name, class name, method name, variable name, etc."},"filePaths":{"type":"array","description":"One or more file paths which likely contain the definition of the symbol. For instance the file which declares a class or function. This is optional but will speed up the invocation of this tool and improve the quality of its output.","items":{"type":"string"}}},"required":["symbolName"]}}},{"type":"function","function":{"name":"list_dir","description":"List the contents of a directory. Result will have the name of the child. If the name ends in /, it's a folder, otherwise a file","parameters":{"type":"object","properties":{"path":{"type":"string","description":"The absolute path to the directory to list."}},"required":["path"]}}},{"type":"function","function":{"name":"multi_replace_string_in_file","description":"This tool allows you to apply multiple replace_string_in_file operations in a single call, which is more efficient than calling replace_string_in_file multiple times. It takes an array of replacement operations and applies them sequentially. Each replacement operation has the same parameters as replace_string_in_file: filePath, oldString, newString, and explanation. This tool is ideal when you need to make multiple edits across different files or multiple edits in the same file. The tool will provide a summary of successful and failed operations.","parameters":{"type":"object","properties":{"explanation":{"type":"string","description":"A brief explanation of what the multi-replace operation will accomplish."},"replacements":{"type":"array","description":"An array of replacement operations to apply sequentially.","items":{"type":"object","properties":{"explanation":{"type":"string","description":"A brief explanation of this specific replacement operation."},"filePath":{"type":"string","description":"An absolute path to the file to edit."},"oldString":{"type":"string","description":"The exact literal text to replace, preferably unescaped. Include at least 3 lines of context BEFORE and AFTER the target text, matching whitespace and indentation precisely. If this string is not the exact literal text or does not match exactly, this replacement will fail."},"newString":{"type":"string","description":"The exact literal text to replace oldString with, preferably unescaped. Provide the EXACT text. Ensure the resulting code is correct and idiomatic."}},"required":["explanation","filePath","oldString","newString"]},"minItems":1}},"required":["explanation","replacements"]}}},{"type":"function","function":{"name":"read_file","description":"Read the contents of a file.\n\nYou must specify the line range you're interested in. Line numbers are 1-indexed. If the file contents returned are insufficient for your task, you may call this tool again to retrieve more content. Prefer reading larger ranges over doing many small reads.","parameters":{"type":"object","properties":{"filePath":{"description":"The absolute path of the file to read.","type":"string"},"startLine":{"type":"number","description":"The line number to start reading from, 1-based."},"endLine":{"type":"number","description":"The inclusive line number to end reading at, 1-based."}},"required":["filePath","startLine","endLine"]}}},{"type":"function","function":{"name":"read_notebook_cell_output","description":"This tool will retrieve the output for a notebook cell from its most recent execution or restored from disk. The cell may have output even when it has not been run in the current kernel session. This tool has a higher token limit for output length than the runNotebookCell tool.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file with the cell to run, or the URI of a untitled, not yet named, file, such as untitled:Untitled-1.ipynb"},"cellId":{"type":"string","description":"The ID of the cell for which output should be retrieved."}},"required":["filePath","cellId"]}}},{"type":"function","function":{"name":"replace_string_in_file","description":"This is a tool for making edits in an existing file in the workspace. For moving or renaming files, use run in terminal tool with the 'mv' command instead. For larger edits, split them into smaller edits and call the edit tool multiple times to ensure accuracy. Before editing, always ensure you have the context to understand the file's contents and context. To edit a file, provide: 1) filePath (absolute path), 2) oldString (MUST be the exact literal text to replace including all whitespace, indentation, newlines, and surrounding code etc), and 3) newString (MUST be the exact literal text to replace \\oldString\ with (also including all whitespace, indentation, newlines, and surrounding code etc.). Ensure the resulting code is correct and idiomatic.). Each use of this tool replaces exactly ONE occurrence of oldString.\n\nCRITICAL for \\oldString\: Must uniquely identify the single instance to change. Include at least 3 lines of context BEFORE and AFTER the target text, matching whitespace and indentation precisely. If this string matches multiple locations, or does not match exactly, the tool will fail. Never use 'Lines 123-456 omitted' from summarized documents or ...existing code... comments in the oldString or newString.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the file to edit."},"oldString":{"type":"string","description":"The exact literal text to replace, preferably unescaped. For single replacements (default), include at least 3 lines of context BEFORE and AFTER the target text, matching whitespace and indentation precisely. For multiple replacements, specify expected_replacements parameter. If this string is not the exact literal text (i.e. you escaped it) or does not match exactly, the tool will fail."},"newString":{"type":"string","description":"The exact literal text to replace old_stringwith, preferably unescaped. Provide the EXACT text. Ensure the resulting code is correct and idiomatic."}},"required":["filePath","oldString","newString"]}}},{"type":"function","function":{"name":"run_notebook_cell","description":"This is a tool for running a code cell in a notebook file directly in the notebook editor. The output from the execution will be returned. Code cells should be run as they are added or edited when working through a problem to bring the kernel state up to date and ensure the code executes successfully. Code cells are ready to run and don't require any pre-processing. If asked to run the first cell in a notebook, you should run the first code cell since markdown cells cannot be executed. NOTE: Avoid executing Markdown cells or providing Markdown cell IDs, as Markdown cells cannot be executed.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file with the cell to run, or the URI of a untitled, not yet named, file, such asuntitled:Untitled-1.ipynb"},"reason":{"type":"string","description":"An optional explanation of why the cell is being run. This will be shown to the user before the tool is run and is not necessary if it's self-explanatory."},"cellId":{"type":"string","description":"The ID for the code cell to execute. Avoid providing markdown cell IDs as nothing will be executed."},"continueOnError":{"type":"boolean","description":"Whether or not execution should continue for remaining cells if an error is encountered. Default to false unless instructed otherwise."}},"required":["filePath","cellId"]}}},{"type":"function","function":{"name":"run_vscode_command","description":"Run a command in VS Code. Use this tool to run a command in Visual Studio Code as part of a new workspace creation process only.","parameters":{"type":"object","properties":{"commandId":{"type":"string","description":"The ID of the command to execute. This should be in the format ."},"name":{"type":"string","description":"The name of the command to execute. This should be a clear and concise description of the command."},"args":{"type":"array","description":"The arguments to pass to the command. This should be an array of strings.","items":{"type":"string"}}},"required":["commandId","name"]}}},{"type":"function","function":{"name":"semantic_search","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.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to search the codebase for. Should contain all relevant context. Should ideally be text that might appear in the codebase, such as function names, variable names, or comments."}},"required":["query"]}}},{"type":"function","function":{"name":"test_failure","description":"Includes test failure information in the prompt.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"vscode_searchExtensions_internal","description":"This is a tool for browsing Visual Studio Code Extensions Marketplace. It allows the model to search for extensions and retrieve detailed information about them. The model should use this tool whenever it needs to discover extensions or resolve information about known ones. To use the tool, the model has to provide the category of the extensions, relevant search keywords, or known extension IDs. Note that search results may include false positives, so reviewing and filtering is recommended.","parameters":{"type":"object","properties":{"category":{"type":"string","description":"The category of extensions to search for","enum":["AI","Azure","Chat","Data Science","Debuggers","Extension Packs","Education","Formatters","Keymaps","Language Packs","Linters","Machine Learning","Notebooks","Programming Languages","SCM Providers","Snippets","Testing","Themes","Visualization","Other"]},"keywords":{"type":"array","items":{"type":"string"},"description":"The keywords to search for"},"ids":{"type":"array","items":{"type":"string"},"description":"The ids of the extensions to search for"}}}}},{"type":"function","function":{"name":"create_and_run_task","description":"Creates and runs a build, run, or custom task for the workspace by generating or adding to a tasks.json file based on the project structure (such as package.json or README.md). If the user asks to build, run, launch and they have no tasks.json file, use this tool. If they ask to create or add a task, use this tool.","parameters":{"type":"object","properties":{"workspaceFolder":{"type":"string","description":"The absolute path of the workspace folder where the tasks.json file will be created."},"task":{"type":"object","description":"The task to add to the new tasks.json file.","properties":{"label":{"type":"string","description":"The label of the task."},"type":{"type":"string","description":"The type of the task. The only supported value is 'shell'.","enum":["shell"]},"command":{"type":"string","description":"The shell command to run for the task. Use this to specify commands for building or running the application."},"args":{"type":"array","description":"The arguments to pass to the command.","items":{"type":"string"}},"isBackground":{"type":"boolean","description":"Whether the task runs in the background without blocking the UI or other tasks. Set to true for long-running processes like watch tasks or servers that should continue executing without requiring user attention. When false, the task will block the terminal until completion."},"problemMatcher":{"type":"array","description":"The problem matcher to use to parse task output for errors and warnings. Can be a predefined matcher like '$tsc' (TypeScript), '$eslint - stylish', '$gcc', etc., or a custom pattern defined in tasks.json. This helps VS Code display errors in the Problems panel and enables quick navigation to error locations.","items":{"type":"string"}},"group":{"type":"string","description":"The group to which the task belongs."}},"required":["label","type","command"]}},"required":["task","workspaceFolder"]}}},{"type":"function","function":{"name":"get_terminal_output","description":"Get the output of a terminal command previously started with run_in_terminal","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The ID of the terminal to check."}},"required":["id"]}}},{"type":"function","function":{"name":"manage_todo_list","description":"Manage a structured todo list to track progress and plan tasks throughout your coding session. Use this tool VERY frequently to ensure task visibility and proper planning.\n\nWhen to use this tool:\n- Complex multi-step work requiring planning and tracking\n- When user provides multiple tasks or requests (numbered/comma-separated)\n- After receiving new instructions that require multiple steps\n- BEFORE starting work on any todo (mark as in-progress)\n- IMMEDIATELY after completing each todo (mark completed individually)\n- When breaking down larger tasks into smaller actionable steps\n- To give users visibility into your progress and planning\n\nWhen NOT to use:\n- Single, trivial tasks that can be completed in one step\n- Purely conversational/informational requests\n- When just reading files or performing simple searches\n\nCRITICAL workflow:\n1. Plan tasks by writing todo list with specific, actionable items\n2. Mark ONE todo as in-progress before starting work\n3. Complete the work for that specific todo\n4. Mark that todo as completed IMMEDIATELY\n5. Move to next todo and repeat\n\nTodo states:\n- not-started: Todo not yet begun\n- in-progress: Currently working (limit ONE at a time)\n- completed: Finished successfully\n\nIMPORTANT: Mark todos completed as soon as they are done. Do not batch completions.","parameters":{"type":"object","properties":{"todoList":{"type":"array","description":"Complete array of all todo items (required for write operation, ignored for read). Must include ALL items - both existing and new.","items":{"type":"object","properties":{"id":{"type":"number","description":"Unique identifier for the todo. Use sequential numbers starting from 1."},"title":{"type":"string","description":"Concise action-oriented todo label (3-7 words). Displayed in UI."},"description":{"type":"string","description":"Detailed context, requirements, or implementation notes. Include file paths, specific methods, or acceptance criteria."},"status":{"type":"string","enum":["not-started","in-progress","completed"],"description":"not-started: Not begun | in-progress: Currently working (max 1) | completed: Fully finished with no blockers"}},"required":["id","title","description","status"]}},"operation":{"type":"string","enum":["write","read"],"description":"write: Replace entire todo list with new content. read: Retrieve current todo list. ALWAYS provide complete list when writing - partial updates not supported."}},"required":["operation"]}}},{"type":"function","function":{"name":"run_in_terminal","description":"This tool allows you to execute Windows PowerShell 5.1 commands in a persistent terminal session, preserving environment variables, working directory, and other context across multiple commands.\n\nCommand Execution:\n- Use semicolons ; to chain commands on one line, NEVER use && even when asked explicitly\n- Prefer pipelines | for object-based data flow\n- Never create a sub-shell (eg. powershell -c "command") unless explicitly asked\n\nDirectory Management:\n- Must use absolute paths to avoid navigation issues\n- Use $PWD or Get-Location for current directory\n- Use Push-Location/Pop-Location for directory stack\n\nProgram Execution:\n- Supports .NET, Python, Node.js, and other executables\n- Install modules via Install-Module, Install-Package\n- Use Get-Command to verify cmdlet/function availability\n\nBackground Processes:\n- For long-running tasks (e.g., servers), set isBackground=true\n- Returns a terminal ID for checking status and runtime later\n- Use Start-Job for background PowerShell jobs\n\nOutput Management:\n- Output is automatically truncated if longer than 60KB to prevent context overflow\n- Use Select-Object, Where-Object, Format-Table to filter output\n- Use -First/-Last parameters to limit results\n- For pager commands, add | Out-String or | Format-List\n\nBest Practices:\n- Use proper cmdlet names instead of aliases in scripts\n- Quote paths with spaces: "C:\Path With Spaces"\n- Prefer PowerShell cmdlets over external commands when available\n- Prefer idiomatic PowerShell like Get-ChildItem instead of dir or ls for file listings\n- Use Test-Path to check file/directory existence\n- Be specific with Select-Object properties to avoid excessive output","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The command to run in the terminal."},"explanation":{"type":"string","description":"A one-sentence description of what the command does. This will be shown to the user before the command is run."},"isBackground":{"type":"boolean","description":"Whether the command starts a background process. If true, the command will run in the background and you will not see the output. If false, the tool call will block on the command finishing, and then you will get the output. Examples of background processes: building in watch mode, starting a server. You can check the output of a background process later on by using get_terminal_output."}},"required":["command","explanation","isBackground"]}}},{"type":"function","function":{"name":"runSubagent","description":"Launch a new agent to handle complex, multi-step tasks autonomously. This tool is good at researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use this agent to perform the search for you.\n\n- Agents do not run async or in the background, you will wait for the agent's result.\n- When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.\n- Each agent invocation is stateless. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.\n- The agent's outputs should generally be trusted\n- Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n- If the user asks for a certain agent, you MUST provide that EXACT agent name (case-sensitive) to invoke that specific agent.","parameters":{"type":"object","properties":{"prompt":{"type":"string","description":"A detailed description of the task for the agent to perform"},"description":{"type":"string","description":"A short (3-5 word) description of the task"},"agentName":{"type":"string","description":"Optional name of a specific agent to invoke. If not provided, uses the current agent."}},"required":["prompt","description"]}}},{"type":"function","function":{"name":"terminal_last_command","description":"Get the last command run in the active terminal.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"terminal_selection","description":"Get the current selection in the active terminal.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_pull_request_review_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is focused on managing pull request reviews within GitHub repositories. They allow users to add comments to pending reviews, create new reviews, submit existing pending reviews, and delete them if necessary. The tools facilitate collaboration by enabling reviewers to provide feedback on code changes before they are merged into the main branch. Users can create a new review or submit an existing one, ensuring that the review process is efficient and organized.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_repository_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis collection of tools is designed for comprehensive management of GitHub repositories. Users can create new repositories, branches, and pull requests, as well as create or update files and issues. The tools also allow for the addition of comments to issues and pull requests, enhancing communication among team members. By utilizing these tools, developers can effectively manage their codebase, track issues, and collaborate on changes, ensuring a smooth workflow in software development.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_repository_inspection_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group provides tools for inspecting various elements within a GitHub repository. Users can retrieve details about commits, file contents, labels, releases, and tags. These tools are essential for understanding the history and structure of a repository, allowing developers to analyze changes, track progress, and gather information about specific components. By leveraging these inspection tools, users can make informed decisions about code modifications and repository management.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_release_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis set of tools focuses on managing releases and tags within GitHub repositories. Users can list all releases, retrieve specific releases by tag name, and list all tags associated with a repository. These tools are crucial for version control and deployment processes, enabling developers to track software versions and manage updates effectively. By using these tools, teams can ensure that they are working with the correct versions of their software and can easily access historical releases.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_search_and_discovery_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is dedicated to searching and discovering various elements within GitHub. Users can search for code, repositories, and users, making it easier to locate specific projects, contributors, or code snippets. These tools enhance the ability to find relevant information quickly, whether for collaboration, research, or learning purposes. By utilizing these search capabilities, developers can efficiently navigate the vast ecosystem of GitHub and connect with the right resources.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_branch_and_commit_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis collection of tools is focused on managing branches and commits within GitHub repositories. Users can list all branches in a repository and retrieve a list of commits associated with a specific branch. These tools are essential for understanding the development history and current state of a project. By using these tools, developers can track changes, manage feature branches, and ensure that their work is organized and aligned with the overall project goals.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_pull_request_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is designed for managing pull requests within GitHub repositories. Users can list all pull requests, retrieve information about specific pull requests, search for pull requests using specific criteria, and update the branch of a pull request with the latest changes. These tools facilitate the review and integration of code changes, ensuring that contributions are properly evaluated and merged into the main codebase. By utilizing these tools, teams can streamline their code review process and maintain high-quality standards.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"mcp_io_github_git_assign_copilot_to_issue","description":"Assign Copilot to a specific issue in a GitHub repository.\n\nThis tool can help with the following outcomes:\n- a Pull Request created with source code changes to resolve the issue\n\n\nMore information can be found at:\n- https://docs.github.com/en/copilot/using-github-copilot/using-copilot-coding-agent-to-work-on-tasks/about-assigning-tasks-to-copilot\n","parameters":{"type":"object","required":["owner","repo","issueNumber"],"properties":{"issueNumber":{"type":"number","description":"Issue number"},"owner":{"type":"string","description":"Repository owner"},"repo":{"type":"string","description":"Repository name"}}}}},{"type":"function","function":{"name":"mcp_io_github_git_delete_file","description":"Delete a file from a GitHub repository","parameters":{"type":"object","required":["owner","repo","path","message","branch"],"properties":{"branch":{"type":"string","description":"Branch to delete the file from"},"message":{"type":"string","description":"Commit message"},"owner":{"type":"string","description":"Repository owner (username or organization)"},"path":{"type":"string","description":"Path to the file to delete"},"repo":{"type":"string","description":"Repository name"}}}}},{"type":"function","function":{"name":"mcp_io_github_git_fork_repository","description":"Fork a GitHub repository to your account or specified organization","parameters":{"type":"object","required":["owner","repo"],"properties":{"organization":{"type":"string","description":"Organization to fork to"},"owner":{"type":"string","description":"Repository owner"},"repo":{"type":"string","description":"Repository name"}}}}},{"type":"function","function":{"name":"mcp_io_github_git_get_teams","description":"Get details of the teams the user is a member of. Limited to organizations accessible with current credentials","parameters":{"type":"object","properties":{"user":{"type":"string","description":"Username to get teams for. If not provided, uses the authenticated user."}}}}},{"type":"function","function":{"name":"mcp_io_github_git_list_issue_types","description":"List supported issue types for repository owner (organization).","parameters":{"type":"object","required":["owner"],"properties":{"owner":{"type":"string","description":"The organization owner of the repository"}}}}},{"type":"function","function":{"name":"mcp_io_github_git_list_issues","description":"List issues in a GitHub repository. For pagination, use the 'endCursor' from the previous response's 'pageInfo' in the 'after' parameter.","parameters":{"type":"object","required":["owner","repo"],"properties":{"after":{"type":"string","description":"Cursor for pagination. Use the endCursor from the previous page's PageInfo for GraphQL APIs."},"direction":{"type":"string","description":"Order direction. If provided, the 'orderBy' also needs to be provided.","enum":["ASC","DESC"]},"labels":{"type":"array","description":"Filter by labels","items":{"type":"string"}},"orderBy":{"type":"string","description":"Order issues by field. If provided, the 'direction' also needs to be provided.","enum":["CREATED_AT","UPDATED_AT","COMMENTS"]},"owner":{"type":"string","description":"Repository owner"},"perPage":{"type":"number","description":"Results per page for pagination (min 1, max 100)","minimum":1,"maximum":100},"repo":{"type":"string","description":"Repository name"},"since":{"type":"string","description":"Filter by date (ISO 8601 timestamp)"},"state":{"type":"string","description":"Filter by state, by default both open and closed issues are returned when not provided","enum":["OPEN","CLOSED"]}}}}},{"type":"function","function":{"name":"mcp_io_github_git_push_files","description":"Push multiple files to a GitHub repository in a single commit","parameters":{"type":"object","required":["owner","repo","branch","files","message"],"properties":{"branch":{"type":"string","description":"Branch to push to"},"files":{"type":"array","description":"Array of file objects to push, each object with path (string) and content (string)","items":{"type":"object","required":["path","content"],"properties":{"content":{"type":"string","description":"file content"},"path":{"type":"string","description":"path to the file"}}}},"message":{"type":"string","description":"Commit message"},"owner":{"type":"string","description":"Repository owner"},"repo":{"type":"string","description":"Repository name"}}}}},{"type":"function","function":{"name":"mcp_io_github_git_request_copilot_review","description":"Request a GitHub Copilot code review for a pull request. Use this for automated feedback on pull requests, usually before requesting a human reviewer.","parameters":{"type":"object","required":["owner","repo","pullNumber"],"properties":{"owner":{"type":"string","description":"Repository owner"},"pullNumber":{"type":"number","description":"Pull request number"},"repo":{"type":"string","description":"Repository name"}}}}},{"type":"function","function":{"name":"activate_observation_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is focused on managing observations within a knowledge graph. The 'Add new observations to existing entities in the knowledge graph' tool allows users to enrich existing entities with additional data, enhancing the depth and utility of the knowledge graph. Conversely, the 'Delete specific observations from entities in the knowledge graph' tool provides the capability to remove outdated or incorrect observations, ensuring that the knowledge graph remains accurate and relevant. Together, these tools enable users to maintain the integrity and richness of the knowledge graph by facilitating both the addition and removal of observations as needed.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_entity_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group encompasses tools designed for the creation and deletion of entities and their relationships within a knowledge graph. The 'Create multiple new entities in the knowledge graph' tool allows users to efficiently add new entities, expanding the graph's scope and potential insights. On the other hand, the 'Delete multiple entities and their associated relations from the knowledge graph' tool enables users to remove entities that are no longer relevant, along with their connections, thereby streamlining the graph. Additionally, the 'Delete multiple relations from the knowledge graph' tool allows for targeted removal of specific relationships, providing fine-grained control over the graph's structure. Collectively, these tools empower users to effectively manage the lifecycle of entities and their interconnections within the knowledge graph.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_node_access_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group consists of tools that facilitate access to specific nodes within a knowledge graph. The 'Open specific nodes in the knowledge graph by their names' tool allows users to directly access and view detailed information about particular nodes, making it easier to navigate the graph. Meanwhile, the 'Search for nodes in the knowledge graph based on a query' tool provides a powerful search capability, enabling users to find nodes that match specific criteria or keywords. Together, these tools enhance user interaction with the knowledge graph by simplifying the process of locating and accessing relevant nodes, thereby improving the overall usability and efficiency of knowledge exploration.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"mcp_memory_create_relations","description":"Create multiple new relations between entities in the knowledge graph. Relations should be in active voice","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","type":"object","properties":{"relations":{"type":"array","items":{"type":"object","properties":{"from":{"description":"The name of the entity where the relation starts","type":"string"},"to":{"description":"The name of the entity where the relation ends","type":"string"},"relationType":{"description":"The type of the relation","type":"string"}},"required":["from","to","relationType"]}}},"required":["relations"]}}},{"type":"function","function":{"name":"mcp_memory_read_graph","description":"Read the entire knowledge graph","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_web_browser_interaction_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is designed to facilitate various interactions with web browsers, enabling automated navigation and manipulation of web pages. Each tool serves a specific function that contributes to a seamless browsing experience, making it ideal for tasks such as web scraping, automated testing, or user simulation. \n\nThe tools include functionalities for performing clicks on web elements, handling dialog boxes, and navigating to specific URLs. This allows users to automate the process of interacting with web applications, which can be particularly useful for testing user interfaces or gathering data from websites. \n\nAdditionally, the ability to hover over elements and select options from dropdown menus enhances the capability to interact with dynamic web content. Users can simulate user behavior more accurately, which is essential for testing scenarios where user input is required. \n\nThe tools also provide options for keyboard interactions, such as pressing keys and typing text into editable fields, which further expands the range of automated tasks that can be performed. This is particularly useful for filling out forms or executing keyboard shortcuts within web applications. \n\nFinally, the ability to resize the browser window and navigate back to previous pages adds flexibility to the automation process, allowing users to create more complex workflows that mimic real user behavior. Together, these tools create a robust suite for automating web interactions, enhancing productivity and efficiency in web-based tasks.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_form_and_file_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group focuses on managing forms and file uploads within web applications. The tools included allow users to fill out multiple form fields efficiently, which is essential for automating data entry tasks in scenarios such as user registration, surveys, or any application requiring user input. By automating the filling of forms, users can save time and reduce the likelihood of errors associated with manual entry.\n\nIn addition to form filling, the tools also provide capabilities for uploading one or multiple files. This is particularly useful in applications where users need to submit documents, images, or other files as part of their interaction with the web service. The ability to automate file uploads can significantly enhance user experience and streamline processes that involve document submission.\n\nTogether, these tools enable comprehensive management of user input and file handling in web applications. They can be utilized in testing environments to simulate user behavior or in production environments to automate repetitive tasks, ensuring that data is entered accurately and efficiently. This combination of form and file management capabilities is crucial for developers and testers looking to enhance their web application workflows.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"activate_web_page_capture_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group consists of tools designed for capturing visual representations of web pages, specifically focusing on accessibility and standard screenshots. The 'mcp_microsoft_pla_browser_snapshot' tool allows users to capture an accessibility snapshot of the current page, which is more informative than a traditional screenshot as it provides insights into the page's accessibility features. This is particularly useful for developers and designers who need to ensure their web content is accessible to all users, including those with disabilities.\n\nOn the other hand, the 'mcp_microsoft_pla_browser_take_screenshot' tool enables users to take a standard screenshot of the current page. While this tool is straightforward and captures the visual layout of the page, it does not provide the interactive capabilities that the accessibility snapshot offers. Users can utilize this tool for quick visual documentation or sharing of the page's appearance.\n\nTogether, these tools can be used in a complementary manner. For instance, a web developer might first take an accessibility snapshot to evaluate how well the page meets accessibility standards and then follow up with a screenshot to document the visual design for stakeholders. This dual approach ensures that both functional and aesthetic aspects of the web page are considered.\n\nThese tools are particularly valuable in web development and design workflows, where understanding both the visual and functional accessibility of a page is crucial. By integrating these tools into their processes, teams can enhance their ability to create inclusive and user-friendly web experiences.\n\nOverall, the web_page_capture_tools group provides essential functionalities for capturing and analyzing web pages, making them indispensable for anyone involved in web development, design, or accessibility auditing.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_console_messages","description":"Returns all console messages","parameters":{"type":"object","properties":{"level":{"type":"string","enum":["error","warning","info","debug"],"default":"info","description":"Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info"."}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_drag","description":"Perform drag and drop between two elements","parameters":{"type":"object","properties":{"startElement":{"type":"string","description":"Human-readable source element description used to obtain the permission to interact with the element"},"startRef":{"type":"string","description":"Exact source element reference from the page snapshot"},"endElement":{"type":"string","description":"Human-readable target element description used to obtain the permission to interact with the element"},"endRef":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["startElement","startRef","endElement","endRef"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_evaluate","description":"Evaluate JavaScript expression on page or element","parameters":{"type":"object","properties":{"function":{"type":"string","description":"() => { / code / } or (element) => { / code */ } when element is provided"},"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["function"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_install","description":"Install the browser specified in the config. Call this if you get an error about the browser not being installed.","parameters":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_network_requests","description":"Returns all network requests since loading the page","parameters":{"type":"object","properties":{"includeStatic":{"type":"boolean","default":false,"description":"Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false."}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_run_code","description":"Run Playwright code snippet","parameters":{"type":"object","properties":{"code":{"type":"string","description":"A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }"}},"required":["code"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_tabs","description":"List, create, close, or select a browser tab.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":["list","new","close","select"],"description":"Operation to perform"},"index":{"type":"number","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_wait_for","description":"Wait for text to appear or disappear or a specified time to pass","parameters":{"type":"object","properties":{"time":{"type":"number","description":"The time to wait in seconds"},"text":{"type":"string","description":"The text to wait for"},"textGone":{"type":"string","description":"The text to wait for to disappear"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_navigate","description":"Navigate to a URL","parameters":{"type":"object","properties":{"url":{"type":"string","description":"The URL to navigate to"}},"required":["url"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_navigate_back","description":"Go back to the previous page","parameters":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_handle_dialog","description":"Handle a dialog","parameters":{"type":"object","properties":{"accept":{"type":"boolean","description":"Whether to accept the dialog."},"promptText":{"type":"string","description":"The text of the prompt in case of a prompt dialog."}},"required":["accept"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_close","description":"Close the page","parameters":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_select_option","description":"Select an option in a dropdown","parameters":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"values":{"type":"array","items":{"type":"string"},"description":"Array of values to select in the dropdown. This can be a single value or multiple values."}},"required":["element","ref","values"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_type","description":"Type text into editable element","parameters":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"text":{"type":"string","description":"Text to type into the element"},"submit":{"type":"boolean","description":"Whether to submit entered text (press Enter after)"},"slowly":{"type":"boolean","description":"Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once."}},"required":["element","ref","text"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}}],"tool_choice":"auto"}

=== API REQUEST 1 ===
Timestamp: 2025-12-17T13:18:32.0139485+03:00
Upstream URL: https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:streamGenerateContent?alt=sse
HTTP Method: POST
Auth: provider=antigravity, auth_id=antigravity-ahmedgrageh_gmail_com.json, label=[email protected], type=oauth account=[email protected]

Headers:
Accept: text/event-stream
Authorization: Bearer ya29...0213
Content-Type: application/json
User-Agent: antigravity/1.11.5 windows/amd64

Body:
{"project":"optimal-hallway-qvrh3","request":{"contents":[{"role":"user","parts":[{"text":"\u003cenvironment_info\u003e\nThe user's current OS is: Windows\n\u003c/environment_info\u003e\n\u003cworkspace_info\u003e\nI am working in a workspace with the following folders:\n- d:\mcp\Antigravity2api-main \nI am working in a workspace that has the following structure:\n\nAPI.md\nconfig.json\ndocker-compose.yml\nDockerfile\nLICENSE\npackage.json\nQUOTA_FEATURE.md\nREADME.md\nTOKEN_API.md\nclient/\n\teslint.config.js\n\tindex.html\n\tpackage.json\n\tpostcss.config.js\n\tREADME.md\n\ttailwind.config.js\n\tvite.config.js\n\tpublic/\n\tsrc/\n\t\tApp.css\n\t\tApp.jsx\n\t\tindex.css\n\t\tmain.jsx\n\t\tassets/\n\t\tcomponents/\n\t\t\tAuthOverlay.jsx\n\t\t\tCodeBlock.jsx\n\t\t\tErrorBoundary.jsx\n\t\t\tLayout.jsx\n\t\tcontext/\n\t\t\tAuthContext.jsx\n\t\tlib/\n\t\t\tutils.js\n\t\tpages/\n\t\t\tDashboard.jsx\n\t\t\tDocs.jsx\n\t\t\tKeys.jsx\n\t\t\tLogs.jsx\n\t\t\tMonitor.jsx\n\t\t\tSettings.jsx\n\t\t\tTest.jsx\n\t\t\tTokens.jsx\ndata/\n\taccounts.json\n\taccounts000.json\n\tapp_logs.json\n\tquotas.json\npublic/\n\tapp.js\n\tindex.html\n\tstyle.css\n\tassets/\n\t\tindex-BEs7JOvM.js\n\t\tindex-DOSSKk6s.css\n\timages/\nscripts/\n\toauth-server.js\n\trefresh-tokens.js\nsrc/\n\tAntigravityRequester.js\n\tadmin/\n\t\tkey_manager.js\n\t\tlog_manager.js\n\t\tmonitor.js\n\t\troutes.js\n\t\tsession.js\n\t\tsettings_manager.js\n\t\ttoken_admin.js\n\tapi/\n\t\tclient.js\n\tauth/\n\t\tjwt.js\n\t\tquota_manager.js\n\t\ttoken_manager.js\n\tbin/\n\t\tantigravity_requester_android_arm64\n\t\tantigravity_requester_linux_amd64\n\tconfig/\n\t\tconfig.js\n\t\tinit-env.js\n\tconstants/\n\t\toauth.js\n\troutes/\n\t\tadmin.js\n\t\tsd.js\n\tserver/\n\t\tindex.js\n\tutils/\n\t\tconfigReloader.js\n\t\tdeepMerge.js\n\t\tenvParser.js\n\t\tidGenerator.js\n\t\tidle_manager.js\n\t\timageStorage.js\n\t\tlogger.js\n\t\tmemoryManager.js\n\t\tutils.js\ntest/\n\ttest-get-ip.js\n\ttest-image-generation.js\n\ttest-memory.js\n\ttest-request.js\n\ttest-token-rotation.js\n\ttest-transform.js\nuploads/\n\nThis is the state of the context at this point in the conversation. The view of the workspace structure may be truncated. You can use tools to collect more context if needed.\n\u003c/workspace_info\u003e\n"}]},{"role":"user","parts":[{"text":"\u003ccontext\u003e\nThe current date is December 17, 2025.\nTerminals:\nTerminal: powershell\nTerminal: powershell\nLast Command: node test/test-transform.js\nCwd: D:\mcp\Antigravity2api-main\nExit Code: 0\n\n\u003c/context\u003e\n\u003creminderInstructions\u003e\nWhen using the replace_string_in_file tool, include 3-5 lines of unchanged code before and after the string you want to replace, to make it unambiguous which part of the file should be edited.\nFor maximum efficiency, whenever you plan to perform multiple independent edit operations, invoke them simultaneously using multi_replace_string_in_file tool rather than sequentially. This will greatly improve user's cost and time efficiency leading to a better user experience. Do not announce which tool you're using (for example, avoid saying "I'll implement all the changes using multi_replace_string_in_file").\n\n\u003c/reminderInstructions\u003e\n\u003cuserRequest\u003e\nاهلا\n\u003c/userRequest\u003e\n"}]},{"role":"model","parts":[{"text":"أهلاً وسهلاً! 👋\n\nأنا GitHub Copilot، كيف يمكنني مساعدتك اليوم؟\n\nأرى أنك تعمل على مشروع Antigravity2api وهو يبدو كـ API مع واجهة مستخدم React. المشروع يحتوي على:\n\n- Backend: خادم Node.js مع إدارة المفاتيح والتوكنات\n- Frontend: تطبيق React مع Vite و Tailwind CSS\n- Docker: دعم للتشغيل عبر الحاويات\n\nهل تحتاج مساعدة في شيء محدد؟"}]},{"role":"user","parts":[{"text":"\u003ccontext\u003e\nThe current date is December 17, 2025.\nTerminals:\nTerminal: powershell\nTerminal: powershell\nLast Command: node test/test-transform.js\nCwd: D:\mcp\Antigravity2api-main\nExit Code: 0\n\n\u003c/context\u003e\n\u003creminderInstructions\u003e\nWhen using the replace_string_in_file tool, include 3-5 lines of unchanged code before and after the string you want to replace, to make it unambiguous which part of the file should be edited.\nFor maximum efficiency, whenever you plan to perform multiple independent edit operations, invoke them simultaneously using multi_replace_string_in_file tool rather than sequentially. This will greatly improve user's cost and time efficiency leading to a better user experience. Do not announce which tool you're using (for example, avoid saying "I'll implement all the changes using multi_replace_string_in_file").\n\n\u003c/reminderInstructions\u003e\n\u003cuserRequest\u003e\nقم بتحليل كامل المشروع الحالي \n\u003c/userRequest\u003e\n"}]},{"role":"model","parts":[{"functionCall":{"id":"toolu_vrtx_01BxSTBwzftcFSpGg641nkrU::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","name":"read_file","args":{"endLine":100,"filePath":"d:\mcp\Antigravity2api-main\README.md","startLine":1}},"thoughtSignature":"skip_thought_signature_validator"},{"functionCall":{"id":"toolu_vrtx_01F5SYVgR8HkSQ51zXBxzDur::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","name":"read_file","args":{"startLine":1,"endLine":60,"filePath":"d:\mcp\Antigravity2api-main\package.json"}},"thoughtSignature":"skip_thought_signature_validator"},{"functionCall":{"id":"toolu_vrtx_01QGd1pQy41UDPbHVtkgZbB5::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","name":"read_file","args":{"startLine":1,"endLine":150,"filePath":"d:\mcp\Antigravity2api-main\API.md"}},"thoughtSignature":"skip_thought_signature_validator"},{"functionCall":{"id":"toolu_vrtx_01KT9jNbVNTQBhoQscksEiME::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","name":"read_file","args":{"filePath":"d:\mcp\Antigravity2api-main\config.json","startLine":1,"endLine":100}},"thoughtSignature":"skip_thought_signature_validator"}]},{"role":"user","parts":[{"functionResponse":{"id":"toolu_vrtx_01BxSTBwzftcFSpGg641nkrU::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","name":"read_file","response":{"result":""File: d:\\\\mcp\\\\Antigravity2api-main\\\\README.md. Lines 1 to 100 (631 lines total): \nmarkdown\\n# Antigravity to OpenAI API 代理服务\\n\\n将 Google Antigravity API 转换为 OpenAI 兼容格式的代理服务，支持流式响应、工具调用和多账号管理。\\n\\n## 功能特性\\n\\n- ✅ OpenAI API 兼容格式\\n- ✅ 流式和非流式响应\\n- ✅ 工具调用（Function Calling）支持\\n- ✅ 多账号自动轮换（支持多种轮询策略）\\n- ✅ Token 自动刷新\\n- ✅ API Key 认证\\n- ✅ 思维链（Thinking）输出，兼容 OpenAI reasoning_effort 参数和 DeepSeek reasoning_content 格式\\n- ✅ 图片输入支持（Base64 编码）\\n- ✅ 图片生成支持（gemini-3-pro-image 模型）\\n- ✅ Pro 账号随机 ProjectId 支持\\n- ✅ 模型额度查看（实时显示剩余额度和重置时间）\\n- ✅ SD WebUI API 兼容（支持 txt2img/img2img）\\n- ✅ 心跳机制（防止 Cloudflare 超时断连）\\n- ✅ 模型列表缓存（减少 API 请求）\\n- ✅ 资格校验自动回退（无资格时自动生成随机 ProjectId）\\n- ✅ 真 System 消息合并（开头连续多条 system 与 SystemInstruction 合并）\\n- ✅ 隐私模式（自动隐藏敏感信息）\\n- ✅ 内存优化（从 8+ 进程减少为 2 个进程，内存占用从 100MB+ 降为 50MB+）\\n- ✅ 对象池复用（减少 50%+ 临时对象创建，降低 GC 频率）\\n\\n## 环境要求\\n\\n- Node.js \u003e= 18.0.0\\n\\n## 快速开始\\n\\n### 1. 安装依赖\\n\\n```bash\\nnpm install\\n```\\n\\n### 2. 配置环境变量\\n\\n复制 `.env.example` 为 `.env` 并编辑配置：\\n\\n```bash\\ncp .env.example .env\\n```\\n\\n编辑 `.env` 文件配置必要参数：\\n\\n```env\\n# 必填配置\\nAPI_KEY=sk-text\\nADMIN_USERNAME=admin\\nADMIN_PASSWORD=admin123\\nJWT_SECRET=your-jwt-secret-key-change-this-in-production\\n\\n# 可选配置\\n# PROXY=http://127.0.0.1:7890\\n# SYSTEM_INSTRUCTION=你是聊天机器人\\n# IMAGE_BASE_URL=http://your-domain.com\\n```\\n\\n### 3. 登录获取 Token\\n\\n```bash\\nnpm run login\\n```\\n\\n浏览器会自动打开 Google 授权页面，授权后 Token 会保存到 `data/accounts.json`。\\n\\n### 4. 启动服务\\n\\n```bash\\nnpm start\\n```\\n\\n服务将在 `http://localhost:8045` 启动。\\n\\n## Docker 部署\\n\\n### 使用 Docker Compose（推荐）\\n\\n1. **配置环境变量**\\n\\n创建 `.env` 文件：\\n\\n```bash\\ncp .env.example .env\\n```\\n\\n编辑 `.env` 文件配置必要参数。\\n\\n2. **启动服务**\\n\\n```bash\\ndocker-compose up -d\\n```\\n\\n3. **查看日志**\\n\\n```bash\\n""}}},{"functionResponse":{"id":"toolu_vrtx_01F5SYVgR8HkSQ51zXBxzDur::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","name":"read_file","response":{"result":""json\\n{\\n \\\"name\\\": \\\"antigravity-to-openai\\\",\\n \\\"version\\\": \\\"1.0.0\\\",\\n \\\"description\\\": \\\"Antigravity API 转 OpenAI 格式的代理服务\\\",\\n \\\"type\\\": \\\"module\\\",\\n \\\"main\\\": \\\"src/server/index.js\\\",\\n \\\"scripts\\\": {\\n \\\"start\\\": \\\"node --expose-gc src/server/index.js\\\",\\n \\\"start:no-gc\\\": \\\"node src/server/index.js\\\",\\n \\\"login\\\": \\\"node scripts/oauth-server.js\\\",\\n \\\"refresh\\\": \\\"node scripts/refresh-tokens.js\\\",\\n \\\"dev\\\": \\\"node --expose-gc --watch src/server/index.js\\\"\\n },\\n \\\"keywords\\\": [\\n \\\"antigravity\\\",\\n \\\"openai\\\",\\n \\\"api\\\",\\n \\\"proxy\\\"\\n ],\\n \\\"author\\\": \\\"\\\",\\n \\\"license\\\": \\\"MIT\\\",\\n \\\"dependencies\\\": {\\n \\\"axios\\\": \\\"^1.13.2\\\",\\n \\\"cors\\\": \\\"^2.8.5\\\",\\n \\\"dotenv\\\": \\\"^17.2.3\\\",\\n \\\"express\\\": \\\"^5.2.1\\\",\\n \\\"jsonwebtoken\\\": \\\"^9.0.3\\\"\\n },\\n \\\"engines\\\": {\\n \\\"node\\\": \\\"\u003e=18.0.0\\\"\\n }\\n}\\n\\n""}}},{"functionResponse":{"id":"toolu_vrtx_01QGd1pQy41UDPbHVtkgZbB5::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","name":"read_file","response":{"result":""File: d:\\\\mcp\\\\Antigravity2api-main\\\\API.md. Lines 1 to 150 (501 lines total): \nmarkdown\\n# API 使用文档\\n\\n本文档介绍如何使用 Antigravity2API 提供的 OpenAI 兼容 API。\\n\\n## 基础配置\\n\\n所有 API 请求需要在 Header 中携带 API Key：\\n\\n```\\nAuthorization: Bearer YOUR_API_KEY\\n```\\n\\n默认服务地址：`http://localhost:8045`\\n\\n## 目录\\n\\n- [获取模型列表](#获取模型列表)\\n- [聊天补全](#聊天补全)\\n- [工具调用](#工具调用function-calling)\\n- [图片输入](#图片输入多模态)\\n- [图片生成](#图片生成)\\n- [思维链模型](#思维链模型)\\n- [SD WebUI 兼容 API](#sd-webui-兼容-api)\\n- [管理 API](#管理-api)\\n- [使用示例](#使用示例)\\n\\n## 获取模型列表\\n\\n```bash\\ncurl http://localhost:8045/v1/models \\\\\\n -H \\\"Authorization: Bearer sk-text\\\"\\n```\\n\\n**说明**：模型列表会缓存 1 小时（可通过 `config.json` 的 `cache.modelListTTL` 配置），减少 API 请求。\\n\\n## 聊天补全\\n\\n### 流式响应\\n\\n```bash\\ncurl http://localhost:8045/v1/chat/completions \\\\\\n -H \\\"Content-Type: application/json\\\" \\\\\\n -H \\\"Authorization: Bearer sk-text\\\" \\\\\\n -d '{\\n \\\"model\\\": \\\"gemini-2.0-flash-exp\\\",\\n \\\"messages\\\": [{\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"你好\\\"}],\\n \\\"stream\\\": true\\n }'\\n```\\n\\n### 非流式响应\\n\\n```bash\\ncurl http://localhost:8045/v1/chat/completions \\\\\\n -H \\\"Content-Type: application/json\\\" \\\\\\n -H \\\"Authorization: Bearer sk-text\\\" \\\\\\n -d '{\\n \\\"model\\\": \\\"gemini-2.0-flash-exp\\\",\\n \\\"messages\\\": [{\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"你好\\\"}],\\n \\\"stream\\\": false\\n }'\\n```\\n\\n## 工具调用（Function Calling）\\n\\n```bash\\ncurl http://localhost:8045/v1/chat/completions \\\\\\n -H \\\"Content-Type: application/json\\\" \\\\\\n -H \\\"Authorization: Bearer sk-text\\\" \\\\\\n -d '{\\n \\\"model\\\": \\\"gemini-2.0-flash-exp\\\",\\n \\\"messages\\\": [{\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"北京天气怎么样\\\"}],\\n \\\"tools\\\": [{\\n \\\"type\\\": \\\"function\\\",\\n \\\"function\\\": {\\n \\\"name\\\": \\\"get_weather\\\",\\n \\\"description\\\": \\\"获取天气信息\\\",\\n \\\"parameters\\\": {\\n \\\"type\\\": \\\"object\\\",\\n \\\"properties\\\": {\\n \\\"location\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"城市名称\\\"}\\n },\\n \\\"required\\\": [\\\"location\\\"]\\n }\\n }\\n }]\\n }'\\n```\\n\\n## 图片输入（多模态）\\n\\n支持 Base64 编码的图片输入，兼容 OpenAI 的多模态格式：\\n\\n```bash\\ncurl http://localhost:8045/v1/chat/completions \\\\\\n -H \\\"Content-Type: application/json\\\" \\\\\\n -H \\\"Authorization: Bearer sk-text\\\" \\\\\\n -d '{\\n \\\"model\\\": \\\"gemini-2.0-flash-exp\\\",\\n \\\"messages\\\": [{\\n \\\"role\\\": \\\"user\\\",\\n \\\"content\\\": [\\n {\\\"type\\\": \\\"text\\\", \\\"text\\\": \\\"这张图片里有什么？\\\"},\\n {\\n \\\"type\\\": \\\"image_url\\\",\\n \\\"image_url\\\": {\\n \\\"url\\\": \\\"data:image/jpeg;base64,/9j/4AAQSkZJRg...\\\"\\n }\\n }\\n ]\\n }],\\n \\\"stream\\\": true\\n }'\\n```\\n\\n### 支持的图片格式\\n\\n- JPEG/JPG (`data:image/jpeg;base64,...`)\\n- PNG (`data:image/png;base64,...`)\\n- GIF (`data:image/gif;base64,...`)\\n- WebP (`data:image/webp;base64,...`)\\n\\n## 图片生成\\n\\n支持使用 `gemini-3-pro-image` 模型生成图片，生成的图片会以 Markdown 格式返回：\\n\\n```bash\\ncurl http://localhost:8045/v1/chat/completions \\\\\\n -H \\\"Content-Type: application/json\\\" \\\\\\n -H \\\"Authorization: Bearer sk-text\\\" \\\\\\n -d '{\\n \\\"model\\\": \\\"gemini-3-pro-image\\\",\\n \\\"messages\\\": [{\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"画一只可爱的猫\\\"}],\\n \\\"stream\\\": false\\n }'\\n```\\n\\n**响应示例**：\\n```json\\n{\\n \\\"choices\\\": [{\\n \\\"message\\\": {\\n \\\"role\\\": \\\"assistant\\\",\\n \\\"content\\\": \\\"![image](http://localhost:8045/images/abc123.png)\\\"\\n }\\n }]\\n}\\n```\\n\\n**注意**：\\n""}}},{"functionResponse":{"id":"toolu_vrtx_01KT9jNbVNTQBhoQscksEiME::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","name":"read_file","response":{"result":""json\\n{\\n \\\"server\\\": {\\n \\\"port\\\": 8045,\\n \\\"host\\\": \\\"0.0.0.0\\\",\\n \\\"maxRequestSize\\\": \\\"500mb\\\",\\n \\\"heartbeatInterval\\\": 15000,\\n \\\"memoryThreshold\\\": 25\\n },\\n \\\"rotation\\\": {\\n \\\"strategy\\\": \\\"round_robin\\\",\\n \\\"requestCount\\\": 50\\n },\\n \\\"api\\\": {\\n \\\"url\\\": \\\"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:streamGenerateContent?alt=sse\\\",\\n \\\"modelsUrl\\\": \\\"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:fetchAvailableModels\\\",\\n \\\"noStreamUrl\\\": \\\"https://daily-cloudcode-pa.sandbox.googleapis.com/v1internal:generateContent\\\",\\n \\\"host\\\": \\\"daily-cloudcode-pa.sandbox.googleapis.com\\\",\\n \\\"userAgent\\\": \\\"antigravity/1.11.3 windows/amd64\\\"\\n },\\n \\\"defaults\\\": {\\n \\\"temperature\\\": 1,\\n \\\"topP\\\": 1,\\n \\\"topK\\\": 50,\\n \\\"maxTokens\\\": 32000,\\n \\\"thinkingBudget\\\": 16000\\n },\\n \\\"cache\\\": {\\n \\\"modelListTTL\\\": 3600000\\n },\\n \\\"other\\\": {\\n \\\"timeout\\\": 300000,\\n \\\"skipProjectIdFetch\\\": false,\\n \\\"useNativeAxios\\\": false\\n }\\n}\\n""}}}]},{"role":"model","parts":[{"functionCall":{"id":"toolu_vrtx_01JexGLkACMphw6HpAp4pKr1","name":"read_file","args":{"endLine":150,"filePath":"d:\mcp\Antigravity2api-main\src\server\index.js","startLine":1}},"thoughtSignature":"skip_thought_signature_validator"},{"functionCall":{"id":"toolu_vrtx_01MBoTAxssAYF92Lpe9WPV6i","name":"read_file","args":{"filePath":"d:\mcp\Antigravity2api-main\src\auth\token_manager.js","startLine":1,"endLine":100}},"thoughtSignature":"skip_thought_signature_validator"},{"functionCall":{"id":"toolu_vrtx_01CsBzJvtHUVT8wSUEnzc9Th","name":"read_file","args":{"endLine":100,"filePath":"d:\mcp\Antigravity2api-main\src\AntigravityRequester.js","startLine":1}},"thoughtSignature":"skip_thought_signature_validator"},{"functionCall":{"id":"toolu_vrtx_01JGhV1MYpTuGX4whDEtaBDM","name":"read_file","args":{"filePath":"d:\mcp\Antigravity2api-main\client\package.json","startLine":1,"endLine":50}},"thoughtSignature":"skip_thought_signature_validator"}]},{"role":"user","parts":[{"functionResponse":{"id":"toolu_vrtx_01JexGLkACMphw6HpAp4pKr1","name":"read_file","response":{"result":""File: d:\\\\mcp\\\\Antigravity2api-main\\\\src\\\\server\\\\index.js. Lines 1 to 150 (361 lines total): \njavascript\\nimport express from 'express';\\nimport cors from 'cors';\\nimport path from 'path';\\nimport { fileURLToPath } from 'url';\\nimport { generateAssistantResponse, generateAssistantResponseNoStream, getAvailableModels, generateImageForSD, closeRequester } from '../api/client.js';\\nimport { generateRequestBody } from '../utils/utils.js';\\nimport logger from '../utils/logger.js';\\nimport config from '../config/config.js';\\nimport tokenManager from '../auth/token_manager.js';\\nimport adminRouter from '../routes/admin.js';\\nimport sdRouter from '../routes/sd.js';\\nimport memoryManager, { MemoryPressure } from '../utils/memoryManager.js';\\n\\nconst __filename = fileURLToPath(import.meta.url);\\nconst __dirname = path.dirname(__filename);\\n\\nconst app = express();\\n\\n// ==================== 心跳机制（防止 CF 超时） ====================\\nconst HEARTBEAT_INTERVAL = config.server.heartbeatInterval || 15000; // 从配置读取心跳间隔\\nconst SSE_HEARTBEAT = Buffer.from(': heartbeat\\\\n\\\\n');\\n\\n// 创建心跳定时器\\nconst createHeartbeat = (res) =\u003e {\\n const timer = setInterval(() =\u003e {\\n if (!res.writableEnded) {\\n res.write(SSE_HEARTBEAT);\\n } else {\\n clearInterval(timer);\\n }\\n }, HEARTBEAT_INTERVAL);\\n \\n // 响应结束时清理\\n res.on('close', () =\u003e clearInterval(timer));\\n res.on('finish', () =\u003e clearInterval(timer));\\n \\n return timer;\\n};\\n\\n// 预编译的常量字符串（避免重复创建）\\nconst SSE_PREFIX = Buffer.from('data: ');\\nconst SSE_SUFFIX = Buffer.from('\\\\n\\\\n');\\nconst SSE_DONE = Buffer.from('data: [DONE]\\\\n\\\\n');\\n\\n// 工具函数：生成响应元数据\\nconst createResponseMeta = () =\u003e ({\\n id: `chatcmpl-${Date.now()}`,\\n created: Math.floor(Date.now() / 1000)\\n});\\n\\n// 工具函数：设置流式响应头\\nconst setStreamHeaders = (res) =\u003e {\\n res.setHeader('Content-Type', 'text/event-stream');\\n res.setHeader('Cache-Control', 'no-cache');\\n res.setHeader('Connection', 'keep-alive');\\n res.setHeader('X-Accel-Buffering', 'no'); // 禁用 nginx 缓冲\\n};\\n\\n// 工具函数：构建流式数据块（使用动态对象池减少 GC）\\n// 支持 DeepSeek 格式的 reasoning_content\\nconst chunkPool = [];\\nconst getChunkObject = () =\u003e chunkPool.pop() || { choices: [{ index: 0, delta: {}, finish_reason: null }] };\\nconst releaseChunkObject = (obj) =\u003e {\\n const maxSize = memoryManager.getPoolSizes().chunk;\\n if (chunkPool.length \u003c maxSize) chunkPool.push(obj);\\n};\\n\\n// 注册内存清理回调\\nmemoryManager.registerCleanup((pressure) =\u003e {\\n const poolSizes = memoryManager.getPoolSizes();\\n // 根据压力缩减对象池\\n while (chunkPool.length \u003e poolSizes.chunk) {\\n chunkPool.pop();\\n }\\n});\\n\\n// 启动内存管理器\\nmemoryManager.start(30000);\\n\\nconst createStreamChunk = (id, created, model, delta, finish_reason = null) =\u003e {\\n const chunk = getChunkObject();\\n chunk.id = id;\\n chunk.object = 'chat.completion.chunk';\\n chunk.created = created;\\n chunk.model = model;\\n chunk.choices[0].delta = delta;\\n chunk.choices[0].finish_reason = finish_reason;\\n return chunk;\\n};\\n\\n// 工具函数：零拷贝写入流式数据\\nconst writeStreamData = (res, data) =\u003e {\\n const json = JSON.stringify(data);\\n // 释放对象回池\\n if (data.choices) releaseChunkObject(data);\\n res.write(SSE_PREFIX);\\n res.write(json);\\n res.write(SSE_SUFFIX);\\n};\\n\\n// 工具函数：结束流式响应\\nconst endStream = (res) =\u003e {\\n res.write(SSE_DONE);\\n res.end();\\n};\\n\\napp.use(cors());\\napp.use(express.json({ limit: config.security.maxRequestSize }));\\n\\n// 静态文件服务\\napp.use('/images', express.static(path.join(__dirname, '../../public/images')));\\napp.use(express.static(path.join(__dirname, '../../public')));\\n\\n// 管理路由\\napp.use('/admin', adminRouter);\\n\\napp.use((err, req, res, next) =\u003e {\\n if (err.type === 'entity.too.large') {\\n return res.status(413).json({ error: `请求体过大，最大支持 ${config.security.maxRequestSize}` });\\n }\\n next(err);\\n});\\n\\napp.use((req, res, next) =\u003e {\\n const ignorePaths = ['/images', '/favicon.ico', '/.well-known', '/sdapi/v1/options', '/sdapi/v1/samplers', '/sdapi/v1/schedulers', '/sdapi/v1/upscalers', '/sdapi/v1/latent-upscale-modes', '/sdapi/v1/sd-vae', '/sdapi/v1/sd-modules'];\\n if (!ignorePaths.some(path =\u003e req.path.startsWith(path))) {\\n const start = Date.now();\\n res.on('finish', () =\u003e {\\n logger.request(req.method, req.path, res.statusCode, Date.now() - start);\\n });\\n }\\n next();\\n});\\napp.use('/sdapi/v1', sdRouter);\\n\\napp.use((req, res, next) =\u003e {\\n if (req.path.startsWith('/v1/')) {\\n const apiKey = config.security?.apiKey;\\n if (apiKey) {\\n const authHeader = req.headers.authorization;\\n const providedKey = authHeader?.startsWith('Bearer ') ? authHeader.slice(7) : authHeader;\\n if (providedKey !== apiKey) {\\n logger.warn(`API Key 验证失败: ${req.method} ${req.path}`);\\n return res.status(401).json({ error: 'Invalid API Key' });\\n }\\n }\\n }\\n next();\\n});\\n\\n""}}},{"functionResponse":{"id":"toolu_vrtx_01MBoTAxssAYF92Lpe9WPV6i","name":"read_file","response":{"result":""File: d:\\\\mcp\\\\Antigravity2api-main\\\\src\\\\auth\\\\token_manager.js. Lines 1 to 100 (477 lines total): \njavascript\\nimport fs from 'fs';\\nimport path from 'path';\\nimport { fileURLToPath } from 'url';\\nimport axios from 'axios';\\nimport { log } from '../utils/logger.js';\\nimport { generateSessionId, generateProjectId } from '../utils/idGenerator.js';\\nimport config, { getConfigJson } from '../config/config.js';\\nimport { OAUTH_CONFIG } from '../constants/oauth.js';\\n\\nconst __filename = fileURLToPath(import.meta.url);\\nconst __dirname = path.dirname(__filename);\\n\\n// 轮询策略枚举\\nconst RotationStrategy = {\\n ROUND_ROBIN: 'round_robin', // 均衡负载：每次请求切换\\n QUOTA_EXHAUSTED: 'quota_exhausted', // 额度耗尽才切换\\n REQUEST_COUNT: 'request_count' // 自定义次数后切换\\n};\\n\\nclass TokenManager {\\n constructor(filePath = path.join(__dirname,'..','..','data' ,'accounts.json')) {\\n this.filePath = filePath;\\n this.tokens = [];\\n this.currentIndex = 0;\\n \\n // 轮询策略相关 - 使用原子操作避免锁\\n this.rotationStrategy = RotationStrategy.ROUND_ROBIN;\\n this.requestCountPerToken = 50; // request_count 策略下每个token请求次数后切换\\n this.tokenRequestCounts = new Map(); // 记录每个token的请求次数\\n \\n this.ensureFileExists();\\n this.initialize();\\n }\\n\\n ensureFileExists() {\\n const dir = path.dirname(this.filePath);\\n if (!fs.existsSync(dir)) {\\n fs.mkdirSync(dir, { recursive: true });\\n }\\n if (!fs.existsSync(this.filePath)) {\\n fs.writeFileSync(this.filePath, '[]', 'utf8');\\n log.info('✓ 已创建账号配置文件');\\n }\\n }\\n\\n async initialize() {\\n try {\\n log.info('正在初始化token管理器...');\\n const data = fs.readFileSync(this.filePath, 'utf8');\\n let tokenArray = JSON.parse(data);\\n \\n this.tokens = tokenArray.filter(token =\u003e token.enable !== false).map(token =\u003e ({\\n ...token,\\n sessionId: generateSessionId()\\n }));\\n \\n this.currentIndex = 0;\\n this.tokenRequestCounts.clear();\\n \\n // 加载轮询策略配置\\n this.loadRotationConfig();\\n \\n if (this.tokens.length === 0) {\\n log.warn('⚠ 暂无可用账号，请使用以下方式添加：');\\n log.warn(' 方式1: 运行 npm run login 命令登录');\\n log.warn(' 方式2: 访问前端管理页面添加账号');\\n } else {\\n log.info(`成功加载 ${this.tokens.length} 个可用token`);\\n if (this.rotationStrategy === RotationStrategy.REQUEST_COUNT) {\\n log.info(`轮询策略: ${this.rotationStrategy}, 每token请求 ${this.requestCountPerToken} 次后切换`);\\n } else {\\n log.info(`轮询策略: ${this.rotationStrategy}`);\\n }\\n }\\n } catch (error) {\\n log.error('初始化token失败:', error.message);\\n this.tokens = [];\\n }\\n }\\n\\n // 加载轮询策略配置\\n loadRotationConfig() {\\n try {\\n const jsonConfig = getConfigJson();\\n if (jsonConfig.rotation) {\\n this.rotationStrategy = jsonConfig.rotation.strategy || RotationStrategy.ROUND_ROBIN;\\n this.requestCountPerToken = jsonConfig.rotation.requestCount || 10;\\n }\\n } catch (error) {\\n log.warn('加载轮询配置失败，使用默认值:', error.message);\\n }\\n }\\n\\n // 更新轮询策略（热更新）\\n updateRotationConfig(strategy, requestCount) {\\n if (strategy \u0026\u0026 Object.values(RotationStrategy).includes(strategy)) {\\n this.rotationStrategy = strategy;\\n }\\n if (requestCount \u0026\u0026 requestCount \u003e 0) {\\n this.requestCountPerToken = requestCount;\\n""}}},{"functionResponse":{"id":"toolu_vrtx_01CsBzJvtHUVT8wSUEnzc9Th","name":"read_file","response":{"result":""File: d:\\\\mcp\\\\Antigravity2api-main\\\\src\\\\AntigravityRequester.js. Lines 1 to 100 (363 lines total): \njavascript\\nimport { spawn } from 'child_process';\\nimport os from 'os';\\nimport path from 'path';\\nimport { fileURLToPath } from 'url';\\nimport fs from 'fs';\\n\\nconst __dirname = path.dirname(fileURLToPath(import.meta.url));\\n\\n// 缓冲区大小警告阈值（不限制，只警告）\\nconst BUFFER_WARNING_SIZE = 50 * 1024 * 1024; // 50MB 警告\\n\\nclass antigravityRequester {\\n constructor(options = {}) {\\n this.binPath = options.binPath;\\n this.executablePath = options.executablePath || this._getExecutablePath();\\n this.proc = null;\\n this.requestId = 0;\\n this.pendingRequests = new Map();\\n this.buffer = '';\\n this.writeQueue = Promise.resolve();\\n this.bufferWarned = false;\\n }\\n\\n _getExecutablePath() {\\n const platform = os.platform();\\n const arch = os.arch();\\n \\n let filename;\\n if (platform === 'win32') {\\n filename = 'antigravity_requester_windows_amd64.exe';\\n } else if (platform === 'android') {\\n filename = 'antigravity_requester_android_arm64';\\n } else if (platform === 'linux') {\\n filename = 'antigravity_requester_linux_amd64';\\n } else {\\n throw new Error(`Unsupported platform: ${platform}`);\\n }\\n \\n const binPath = this.binPath || path.join(__dirname, 'bin');\\n const requester_execPath = path.join(binPath, filename);\\n // 设置执行权限（非Windows平台）\\n if (platform !== 'win32') {\\n try {\\n fs.chmodSync(requester_execPath, 0o755);\\n } catch (error) {\\n console.warn(`Could not set executable permissions: ${error.message}`);\\n }\\n }\\n return requester_execPath;\\n }\\n\\n _ensureProcess() {\\n if (this.proc) return;\\n\\n this.proc = spawn(this.executablePath, [], {\\n stdio: ['pipe', 'pipe', 'pipe']\\n });\\n\\n // 设置 stdin 为非阻塞模式\\n if (this.proc.stdin.setDefaultEncoding) {\\n this.proc.stdin.setDefaultEncoding('utf8');\\n }\\n\\n // 增大 stdout 缓冲区以减少背压\\n if (this.proc.stdout.setEncoding) {\\n this.proc.stdout.setEncoding('utf8');\\n }\\n \\n // 使用 setImmediate 异步处理数据,避免阻塞\\n this.proc.stdout.on('data', (data) =\u003e {\\n const chunk = data.toString();\\n \\n // 缓冲区大小监控（仅警告，不限制，因为图片响应可能很大）\\n if (!this.bufferWarned \u0026\u0026 this.buffer.length \u003e BUFFER_WARNING_SIZE) {\\n console.warn(`AntigravityRequester: 缓冲区较大 (${Math.round(this.buffer.length / 1024 / 1024)}MB)，可能有大型响应`);\\n this.bufferWarned = true;\\n }\\n \\n this.buffer += chunk;\\n \\n // 使用 setImmediate 异步处理,避免阻塞 stdout 读取\\n setImmediate(() =\u003e {\\n let start = 0;\\n let end;\\n \\n // 高效的行分割（避免 split 创建大量字符串）\\n while ((end = this.buffer.indexOf('\\\\n', start)) !== -1) {\\n const line = this.buffer.slice(start, end).trim();\\n start = end + 1;\\n \\n if (!line) continue;\\n \\n try {\\n const response = JSON.parse(line);\\n const pending = this.pendingRequests.get(response.id);\\n if (!pending) continue;\\n\\n if (pending.streamResponse) {\\n pending.streamResponse._handleChunk(response);\\n if (response.type === 'end' || response.type === 'error') {\\n""}}},{"functionResponse":{"id":"toolu_vrtx_01JGhV1MYpTuGX4whDEtaBDM","name":"read_file","response":{"result":""json\\n{\\n \\\"name\\\": \\\"client\\\",\\n \\\"private\\\": true,\\n \\\"version\\\": \\\"0.0.0\\\",\\n \\\"type\\\": \\\"module\\\",\\n \\\"scripts\\\": {\\n \\\"dev\\\": \\\"vite\\\",\\n \\\"build\\\": \\\"vite build\\\",\\n \\\"lint\\\": \\\"eslint .\\\",\\n \\\"preview\\\": \\\"vite preview\\\"\\n },\\n \\\"dependencies\\\": {\\n \\\"antigravity-to-openai\\\": \\\"file:..\\\",\\n \\\"clsx\\\": \\\"^2.1.1\\\",\\n \\\"framer-motion\\\": \\\"^12.23.24\\\",\\n \\\"lucide-react\\\": \\\"^0.554.0\\\",\\n \\\"react\\\": \\\"^19.2.0\\\",\\n \\\"react-dom\\\": \\\"^19.2.0\\\",\\n \\\"react-router-dom\\\": \\\"^7.9.6\\\",\\n \\\"tailwind-merge\\\": \\\"^3.4.0\\\"\\n },\\n \\\"devDependencies\\\": {\\n \\\"@eslint/js\\\": \\\"^9.39.1\\\",\\n \\\"@tailwindcss/postcss\\\": \\\"^4.1.17\\\",\\n \\\"@types/react\\\": \\\"^19.2.5\\\",\\n \\\"@types/react-dom\\\": \\\"^19.2.3\\\",\\n \\\"@vitejs/plugin-react\\\": \\\"^5.1.1\\\",\\n \\\"autoprefixer\\\": \\\"^10.4.22\\\",\\n \\\"eslint\\\": \\\"^9.39.1\\\",\\n \\\"eslint-plugin-react-hooks\\\": \\\"^7.0.1\\\",\\n \\\"eslint-plugin-react-refresh\\\": \\\"^0.4.24\\\",\\n \\\"globals\\\": \\\"^16.5.0\\\",\\n \\\"postcss\\\": \\\"^8.5.6\\\",\\n \\\"tailwindcss\\\": \\\"^4.1.17\\\",\\n \\\"vite\\\": \\\"npm:[email protected]\\\"\\n },\\n \\\"overrides\\\": {\\n \\\"vite\\\": \\\"npm:[email protected]\\\"\\n }\\n}\\n\\n""}}}]}],"generationConfig":{"temperature":0,"topP":1},"systemInstruction":{"role":"user","parts":[{"text":"You are an expert AI programming assistant, working with a user in the VS Code editor.\nWhen asked for your name, you must respond with "GitHub Copilot". When asked about the model you are using, you must state that you are using gemini-claude-sonnet-4-5 via gemini.\nFollow the user's requirements carefully \u0026 to the letter.\nFollow Microsoft content policies.\nAvoid content that violates copyrights.\nIf you are asked to generate content that is harmful, hateful, racist, sexist, lewd, or violent, only respond with "Sorry, I can't assist with that."\nKeep your answers short and impersonal.\n\u003cinstructions\u003e\nYou are a highly sophisticated automated coding agent with expert-level knowledge across many different programming languages and frameworks.\nThe user will ask a question, or ask you to perform a task, and it may require lots of research to answer correctly. There is a selection of tools that let you perform actions or retrieve helpful context to answer the user's question.\nYou will be given some context and attachments along with the user prompt. You can use them if they are relevant to the task, and ignore them if not. Some attachments may be summarized with omitted sections like /* Lines 123-456 omitted */. You can use the read_file tool to read more context if needed. Never pass this omitted line marker to an edit tool.\nIf you can infer the project type (languages, frameworks, and libraries) from the user's query or the context that you have, make sure to keep them in mind when making changes.\nIf the user wants you to implement a feature and they have not specified the files to edit, first break down the user's request into smaller concepts and think about the kinds of files you need to grasp each concept.\nIf you aren't sure which tool is relevant, you can call multiple tools. You can call tools repeatedly to take actions or gather as much context as needed until you have completed the task fully. Don't give up unless you are sure the request cannot be fulfilled with the tools you have. It's YOUR RESPONSIBILITY to make sure that you have done all you can to collect necessary context.\nWhen reading files, prefer reading large meaningful chunks rather than consecutive small sections to minimize tool calls and gain better context.\nDon't make assumptions about the situation- gather context first, then perform the task or answer the question.\nThink creatively and explore the workspace in order to make a complete fix.\nDon't repeat yourself after a tool call, pick up where you left off.\nNEVER print out a codeblock with file changes unless the user asked for it. Use the appropriate edit tool instead.\nNEVER print out a codeblock with a terminal command to run unless the user asked for it. Use the run_in_terminal tool instead.\nYou don't need to read a file if it's already provided in context.\n\u003c/instructions\u003e\n\u003ctoolUseInstructions\u003e\nIf the user is requesting a code sample, you can answer it directly without using any tools.\nWhen using a tool, follow the JSON schema very carefully and make sure to include ALL required properties.\nNo need to ask permission before using a tool.\nNEVER say the name of a tool to a user. For example, instead of saying that you'll use the run_in_terminal tool, say "I'll run the command in a terminal".\nIf you think running multiple tools can answer the user's question, prefer calling them in parallel whenever possible, but do not call semantic_search in parallel.\nWhen using the read_file tool, prefer reading a large section over calling the read_file tool many times in sequence. You can also think of all the pieces you may be interested in and read them in parallel. Read large enough context to ensure you get what you need.\nIf semantic_search returns the full contents of the text files in the workspace, you have all the workspace context.\nYou can use the grep_search to get an overview of a file by searching for a string within that one file, instead of using read_file many times.\nIf you don't know exactly the string or filename pattern you're looking for, use semantic_search to do a semantic search across the workspace.\nDon't call the run_in_terminal tool multiple times in parallel. Instead, run one command and wait for the output before running the next command.\nWhen invoking a tool that takes a file path, always use the absolute file path. If the file has a scheme like untitled: or vscode-userdata:, then use a URI with the scheme.\nNEVER try to edit a file by running terminal commands unless the user specifically asks for it.\nTools can be disabled by the user. You may see tools used previously in the conversation that are not currently available. Be careful to only use the tools that are currently available to you.\n\u003c/toolUseInstructions\u003e\n\u003cinstruction forToolsWithPrefix="mcp_io"\u003e\nThe GitHub MCP Server provides tools to interact with GitHub platform.\n\nTool selection guidance:\n\t1. Use 'list_' tools for broad, simple retrieval and pagination of all items of a type (e.g., all issues, all PRs, all branches) with basic filtering.\n\t2. Use 'search_' tools for targeted queries with specific criteria, keywords, or complex filters (e.g., issues with certain text, PRs by author, code containing functions).\n\nContext management:\n\t1. Use pagination whenever possible with batches of 5-10 items.\n\t2. Use minimal_output parameter set to true if the full information is not needed to accomplish a task.\n\nTool usage guidance:\n\t1. For 'search_' tools: Use separate 'sort' and 'order' parameters if available for sorting results - do not include 'sort:' syntax in query strings. Query strings should contain only search criteria (e.g., 'org:google language:python'), not sorting instructions. Always call 'get_me' first to understand current user permissions and context. ## Issues\n\nCheck 'list_issue_types' first for organizations to use proper issue types. Use 'search_issues' before creating new issues to avoid duplicates. Always set 'state_reason' when closing issues. ## Pull Requests\n\nPR review workflow: Always use 'pull_request_review_write' with method 'create' to create a pending review, then 'add_comment_to_pending_review' to add comments, and finally 'pull_request_review_write' with method 'submit_pending' to submit the review for complex reviews with line-specific comments.\n\nBefore creating a pull request, search for pull request templates in the repository. Template files are called pull_request_template.md or they're located in '.github/PULL_REQUEST_TEMPLATE' directory. Use the template content to structure the PR description and then call create_pull_request tool.\n\nHere are common scenarios you may encounter, followed by a description of the steps to follow and the tools to use. Match these to user requests:\nIf the user is bootstrapping a new project, you MUST always follow this workflow:\n- STEP 1: Set up a repository for the project unless one has already been set up by the user.\n- STEP 2: If a repository for the project exists, use issues tools to create at least one tracking issue for the project.\nWhen the user requests to search for issues in a repository using natural language, use the semantic_issues_search tool over search_issues.\n\u003c/instruction\u003e\n\u003cnotebookInstructions\u003e\nTo edit notebook files in the workspace, you can use the edit_notebook_file tool.\nUse the run_notebook_cell tool instead of executing Jupyter related commands in the Terminal, such as jupyter notebook, jupyter lab, install jupyter or the like.\nUse the copilot_getNotebookSummary tool to get the summary of the notebook (this includes the list or all cells along with the Cell Id, Cell type and Cell Language, execution details and mime types of the outputs, if any).\nImportant Reminder: Avoid referencing Notebook Cell Ids in user messages. Use cell number instead.\nImportant Reminder: Markdown cells cannot be executed\n\u003c/notebookInstructions\u003e\n\u003coutputFormatting\u003e\nUse proper Markdown formatting in your answers. When referring to a filename or symbol in the user's workspace, wrap it in backticks.\n\u003cexample\u003e\nThe class Person is in src/models/person.ts.\nThe function calculateTotal is defined in lib/utils/math.ts.\nYou can find the configuration in config/app.config.json.\n\u003c/example\u003e\nUse KaTeX for math equations in your answers.\nWrap inline math equations in $.\nWrap more complex blocks of math equations in $$.\n\n\u003c/outputFormatting\u003e\n\n\u003cinstructions\u003e\n\u003cagents\u003e\nHere is a list of agents that can be used when running a subagent.\nEach agent has optionally a description with the agent's purpose and expertise. When asked to run a subagent, choose the most appropriate agent from this list.\nUse the 'runSubagent' tool with the agent name to run the subagent.\n\u003cagent\u003e\n\u003cname\u003ePlan\u003c/name\u003e\n\u003cdescription\u003eResearches and outlines multi-step plans\u003c/description\u003e\n\u003cargumentHint\u003eOutline the goal or problem to research\u003c/argumentHint\u003e\n\u003c/agent\u003e\n\u003c/agents\u003e\n\n\n\u003c/instructions\u003e\n"}]},"tools":[{"functionDeclarations":[{"name":"create_directory","description":"Create a new directory structure in the workspace. Will recursively create all directories in the path, like mkdir -p. You do not need to use this tool before using create_file, that tool will automatically create the needed directories.","parameters":{"type":"object","properties":{"dirPath":{"type":"string","description":"The absolute path to the directory to create."}},"required":["dirPath"]}},{"name":"create_file","description":"This is a tool for creating a new file in the workspace. The file will be created with the specified content. The directory will be created if it does not already exist. Never use this tool to edit a file that already exists.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to create."},"content":{"type":"string","description":"The content to write to the file."}},"required":["filePath","content"]}},{"name":"create_new_jupyter_notebook","description":"Generates a new Jupyter Notebook (.ipynb) in VS Code. Jupyter Notebooks are interactive documents commonly used for data exploration, analysis, visualization, and combining code with narrative text. Prefer creating plain Python files or similar unless a user explicitly requests creating a new Jupyter Notebook or already has a Jupyter Notebook opened or exists in the workspace.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to use to generate the jupyter notebook. This should be a clear and concise description of the notebook the user wants to create."}},"required":["query"]}},{"name":"create_new_workspace","description":"Get comprehensive setup steps to help the user create complete project structures in a VS Code workspace. This tool is designed for full project initialization and scaffolding, not for creating individual files.\n\nWhen to use this tool:\n- User wants to create a new complete project from scratch\n- Setting up entire project frameworks (TypeScript projects, React apps, Node.js servers, etc.)\n- Initializing Model Context Protocol (MCP) servers with full structure\n- Creating VS Code extensions with proper scaffolding\n- Setting up Next.js, Vite, or other framework-based projects\n- User asks for "new project", "create a workspace", "set up a [framework] project"\n- Need to establish complete development environment with dependencies, config files, and folder structure\n\nWhen NOT to use this tool:\n- Creating single files or small code snippets\n- Adding individual files to existing projects\n- Making modifications to existing codebases\n- User asks to "create a file" or "add a component"\n- Simple code examples or demonstrations\n- Debugging or fixing existing code\n\nThis tool provides complete project setup including:\n- Folder structure creation\n- Package.json and dependency management\n- Configuration files (tsconfig, eslint, etc.)\n- Initial boilerplate code\n- Development environment setup\n- Build and run instructions\n\nUse other file creation tools for individual files within existing projects.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to use to generate the new workspace. This should be a clear and concise description of the workspace the user wants to create."}},"required":["query"]}},{"name":"edit_notebook_file","description":"This is a tool for editing an existing Notebook file in the workspace. Generate the "explanation" property first.\nThe system is very smart and can understand how to apply your edits to the notebooks.\nWhen updating the content of an existing cell, ensure newCode preserves whitespace and indentation exactly and does NOT include any code markers such as (...existing code...).","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file to edit, or the URI of a untitled, not yet named, file, such as untitled:Untitled-1."},"cellId":{"type":"string","description":"Id of the cell that needs to be deleted or edited. Use the value TOP, BOTTOMwhen inserting a cell at the top or bottom of the notebook, else provide the id of the cell after which a new cell is to be inserted. Remember, if a cellId is provided and editType=insert, then a cell will be inserted after the cell with the provided cellId."},"newCode":{"type":"string","description":"The code for the new or existing cell to be edited. Code should not be wrapped within <VSCode.Cell> tags. Do NOT include code markers such as (...existing code...) to indicate existing code."},"language":{"type":"string","description":"The language of the cell.markdown, python, javascript, julia, etc."},"editType":{"type":"string","enum":["insert","delete","edit"],"description":"The operation peformed on the cell, whether insert, deleteoredit.\nUse the editTypefield to specify the operation:insertto add a new cell,editto modify an existing cell's content, anddeleteto remove a cell."}},"required":["filePath","editType","cellId"]}},{"name":"fetch_webpage","description":"Fetches the main content from a web page. This tool is useful for summarizing or analyzing the content of a webpage. You should use this tool when you think the user is looking for information from a specific webpage.","parameters":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"An array of URLs to fetch content from."},"query":{"type":"string","description":"The query to search for in the web page's content. This should be a clear and concise description of the content you want to find."}},"required":["urls","query"]}},{"name":"file_search","description":"Search for files in the workspace by glob pattern. This only returns the paths of matching files. Use this tool when you know the exact filename pattern of the files you're searching for. Glob patterns match from the root of the workspace folder. Examples:\n- **/*.{js,ts} to match all js/ts files in the workspace.\n- src/** to match all files under the top-level src folder.\n- **/foo/**/*.js to match all js files under any foo folder in the workspace.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"Search for files with names or paths matching this glob pattern."},"maxResults":{"type":"number","description":"The maximum number of results to return. Do not use this unless necessary, it can slow things down. By default, only some matches are returned. If you use this and don't see what you're looking for, you can try again with a more specific query or a larger maxResults."}},"required":["query"]}},{"name":"grep_search","description":"Do a fast text search in the workspace. Use this tool when you want to search with an exact string or regex. If you are not sure what words will appear in the workspace, prefer using regex patterns with alternation (|) or character classes to search for multiple potential words at once instead of making separate searches. For example, use 'function|method|procedure' to look for all of those words at once. Use includePattern to search within files matching a specific pattern, or in a specific file, using a relative path. Use 'includeIgnoredFiles' to include files normally ignored by .gitignore, other ignore files, andfiles.excludeandsearch.excludesettings. Warning: using this may cause the search to be slower, only set it when you want to search in ignored folders like node_modules or build outputs. Use this tool when you want to see an overview of a particular file, instead of using read_file many times to look for code within a file.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The pattern to search for in files in the workspace. Use regex with alternation (e.g., 'word1|word2|word3') or character classes to find multiple potential words in a single search. Be sure to set the isRegexp property properly to declare whether it's a regex or plain text pattern. Is case-insensitive."},"isRegexp":{"type":"boolean","description":"Whether the pattern is a regex."},"includePattern":{"type":"string","description":"Search files matching this glob pattern. Will be applied to the relative path of files within the workspace. To search recursively inside a folder, use a proper glob pattern like \"src/folder/**\". Do not use | in includePattern."},"maxResults":{"type":"number","description":"The maximum number of results to return. Do not use this unless necessary, it can slow things down. By default, only some matches are returned. If you use this and don't see what you're looking for, you can try again with a more specific query or a larger maxResults."},"includeIgnoredFiles":{"type":"boolean","description":"Whether to include files that would normally be ignored according to .gitignore, other ignore files andfiles.excludeandsearch.excludesettings. Warning: using this may cause the search to be slower. Only set it when you want to search in ignored folders like node_modules or build outputs."}},"required":["query","isRegexp"]}},{"name":"get_changed_files","description":"Get git diffs of current file changes in a git repository. Don't forget that you can use run_in_terminal to run git commands in a terminal as well.","parameters":{"type":"object","properties":{"repositoryPath":{"type":"string","description":"The absolute path to the git repository to look for changes in. If not provided, the active git repository will be used."},"sourceControlState":{"type":"array","items":{"type":"string","enum":["staged","unstaged","merge-conflicts"]},"description":"The kinds of git state to filter by. Allowed values are: 'staged', 'unstaged', and 'merge-conflicts'. If not provided, all states will be included."}}}},{"name":"get_errors","description":"Get any compile or lint errors in a specific file or across all files. If the user mentions errors or problems in a file, they may be referring to these. Use the tool to see the same errors that the user is seeing. If the user asks you to analyze all errors, or does not specify a file, use this tool to gather errors for all files. Also use this tool after editing a file to validate the change.","parameters":{"type":"object","properties":{"filePaths":{"description":"The absolute paths to the files or folders to check for errors. Omit 'filePaths' when retrieving all errors.","type":"array","items":{"type":"string"}}}}},{"name":"copilot_getNotebookSummary","description":"This is a tool returns the list of the Notebook cells along with the id, cell types, line ranges, language, execution information and output mime types for each cell. This is useful to get Cell Ids when executing a notebook or determine what cells have been executed and what order, or what cells have outputs. If required to read contents of a cell use this to determine the line range of a cells, and then use read_file tool to read a specific line range. Requery this tool if the contents of the notebook change.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file with the cell to run, or the URI of a untitled, not yet named, file, such asuntitled:Untitled-1.ipynb"}},"required":["filePath"]}},{"name":"get_project_setup_info","description":"Do not call this tool without first calling the tool to create a workspace. This tool provides a project setup information for a Visual Studio Code workspace based on a project type and programming language.","parameters":{"type":"object","properties":{"projectType":{"type":"string","description":"The type of project to create. Supported values are: 'python-script', 'python-project', 'mcp-server', 'model-context-protocol-server', 'vscode-extension', 'next-js', 'vite' and 'other'"}},"required":["projectType"]}},{"name":"get_search_view_results","description":"The results from the search view","parameters":{"type":"object","properties":{}}},{"name":"get_vscode_api","description":"Get comprehensive VS Code API documentation and references for extension development. This tool provides authoritative documentation for VS Code's extensive API surface, including proposed APIs, contribution points, and best practices. Use this tool for understanding complex VS Code API interactions.\n\nWhen to use this tool:\n- User asks about specific VS Code APIs, interfaces, or extension capabilities\n- Need documentation for VS Code extension contribution points (commands, views, settings, etc.)\n- Questions about proposed APIs and their usage patterns\n- Understanding VS Code extension lifecycle, activation events, and packaging\n- Best practices for VS Code extension development architecture\n- API examples and code patterns for extension features\n- Troubleshooting extension-specific issues or API limitations\n\nWhen NOT to use this tool:\n- Creating simple standalone files or scripts unrelated to VS Code extensions\n- General programming questions not specific to VS Code extension development\n- Questions about using VS Code as an editor (user-facing features)\n- Non-extension related development tasks\n- File creation or editing that doesn't involve VS Code extension APIs\n\nCRITICAL usage guidelines:\n1. Always include specific API names, interfaces, or concepts in your query\n2. Mention the extension feature you're trying to implement\n3. Include context about proposed vs stable APIs when relevant\n4. Reference specific contribution points when asking about extension manifest\n5. Be specific about the VS Code version or API version when known\n\nScope: This tool is for EXTENSION DEVELOPMENT ONLY - building tools that extend VS Code itself, not for general file creation or non-extension programming tasks.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to search vscode documentation for. Should contain all relevant context."}},"required":["query"]}},{"name":"github_repo","description":"Searches a GitHub repository for relevant source code snippets. Only use this tool if the user is very clearly asking for code snippets from a specific GitHub repository. Do not use this tool for Github repos that the user has open in their workspace.","parameters":{"type":"object","properties":{"repo":{"type":"string","description":"The name of the Github repository to search for code in. Should must be formatted as '/'."},"query":{"type":"string","description":"The query to search for repo. Should contain all relevant context."}},"required":["repo","query"]}},{"name":"install_extension","description":"Install an extension in VS Code. Use this tool to install an extension in Visual Studio Code as part of a new workspace creation process only.","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The ID of the extension to install. This should be in the format .."},"name":{"type":"string","description":"The name of the extension to install. This should be a clear and concise description of the extension."}},"required":["id","name"]}},{"name":"list_code_usages","description":"Request to list all usages (references, definitions, implementations etc) of a function, class, method, variable etc. Use this tool when \n1. Looking for a sample implementation of an interface or class\n2. Checking how a function is used throughout the codebase.\n3. Including and updating all usages when changing a function, method, or constructor","parameters":{"type":"object","properties":{"symbolName":{"type":"string","description":"The name of the symbol, such as a function name, class name, method name, variable name, etc."},"filePaths":{"type":"array","description":"One or more file paths which likely contain the definition of the symbol. For instance the file which declares a class or function. This is optional but will speed up the invocation of this tool and improve the quality of its output.","items":{"type":"string"}}},"required":["symbolName"]}},{"name":"list_dir","description":"List the contents of a directory. Result will have the name of the child. If the name ends in /, it's a folder, otherwise a file","parameters":{"type":"object","properties":{"path":{"type":"string","description":"The absolute path to the directory to list."}},"required":["path"]}},{"name":"multi_replace_string_in_file","description":"This tool allows you to apply multiple replace_string_in_file operations in a single call, which is more efficient than calling replace_string_in_file multiple times. It takes an array of replacement operations and applies them sequentially. Each replacement operation has the same parameters as replace_string_in_file: filePath, oldString, newString, and explanation. This tool is ideal when you need to make multiple edits across different files or multiple edits in the same file. The tool will provide a summary of successful and failed operations.","parameters":{"type":"object","properties":{"explanation":{"type":"string","description":"A brief explanation of what the multi-replace operation will accomplish."},"replacements":{"type":"array","description":"An array of replacement operations to apply sequentially.","items":{"type":"object","properties":{"explanation":{"type":"string","description":"A brief explanation of this specific replacement operation."},"filePath":{"type":"string","description":"An absolute path to the file to edit."},"oldString":{"type":"string","description":"The exact literal text to replace, preferably unescaped. Include at least 3 lines of context BEFORE and AFTER the target text, matching whitespace and indentation precisely. If this string is not the exact literal text or does not match exactly, this replacement will fail."},"newString":{"type":"string","description":"The exact literal text to replace oldString with, preferably unescaped. Provide the EXACT text. Ensure the resulting code is correct and idiomatic."}},"required":["explanation","filePath","oldString","newString"]}}},"required":["explanation","replacements"]}},{"name":"read_file","description":"Read the contents of a file.\n\nYou must specify the line range you're interested in. Line numbers are 1-indexed. If the file contents returned are insufficient for your task, you may call this tool again to retrieve more content. Prefer reading larger ranges over doing many small reads.","parameters":{"type":"object","properties":{"filePath":{"description":"The absolute path of the file to read.","type":"string"},"startLine":{"type":"number","description":"The line number to start reading from, 1-based."},"endLine":{"type":"number","description":"The inclusive line number to end reading at, 1-based."}},"required":["filePath","startLine","endLine"]}},{"name":"read_notebook_cell_output","description":"This tool will retrieve the output for a notebook cell from its most recent execution or restored from disk. The cell may have output even when it has not been run in the current kernel session. This tool has a higher token limit for output length than the runNotebookCell tool.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file with the cell to run, or the URI of a untitled, not yet named, file, such as untitled:Untitled-1.ipynb"},"cellId":{"type":"string","description":"The ID of the cell for which output should be retrieved."}},"required":["filePath","cellId"]}},{"name":"replace_string_in_file","description":"This is a tool for making edits in an existing file in the workspace. For moving or renaming files, use run in terminal tool with the 'mv' command instead. For larger edits, split them into smaller edits and call the edit tool multiple times to ensure accuracy. Before editing, always ensure you have the context to understand the file's contents and context. To edit a file, provide: 1) filePath (absolute path), 2) oldString (MUST be the exact literal text to replace including all whitespace, indentation, newlines, and surrounding code etc), and 3) newString (MUST be the exact literal text to replace \\oldString\ with (also including all whitespace, indentation, newlines, and surrounding code etc.). Ensure the resulting code is correct and idiomatic.). Each use of this tool replaces exactly ONE occurrence of oldString.\n\nCRITICAL for \\oldString\: Must uniquely identify the single instance to change. Include at least 3 lines of context BEFORE and AFTER the target text, matching whitespace and indentation precisely. If this string matches multiple locations, or does not match exactly, the tool will fail. Never use 'Lines 123-456 omitted' from summarized documents or ...existing code... comments in the oldString or newString.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the file to edit."},"oldString":{"type":"string","description":"The exact literal text to replace, preferably unescaped. For single replacements (default), include at least 3 lines of context BEFORE and AFTER the target text, matching whitespace and indentation precisely. For multiple replacements, specify expected_replacements parameter. If this string is not the exact literal text (i.e. you escaped it) or does not match exactly, the tool will fail."},"newString":{"type":"string","description":"The exact literal text to replace old_stringwith, preferably unescaped. Provide the EXACT text. Ensure the resulting code is correct and idiomatic."}},"required":["filePath","oldString","newString"]}},{"name":"run_notebook_cell","description":"This is a tool for running a code cell in a notebook file directly in the notebook editor. The output from the execution will be returned. Code cells should be run as they are added or edited when working through a problem to bring the kernel state up to date and ensure the code executes successfully. Code cells are ready to run and don't require any pre-processing. If asked to run the first cell in a notebook, you should run the first code cell since markdown cells cannot be executed. NOTE: Avoid executing Markdown cells or providing Markdown cell IDs, as Markdown cells cannot be executed.","parameters":{"type":"object","properties":{"filePath":{"type":"string","description":"An absolute path to the notebook file with the cell to run, or the URI of a untitled, not yet named, file, such asuntitled:Untitled-1.ipynb"},"reason":{"type":"string","description":"An optional explanation of why the cell is being run. This will be shown to the user before the tool is run and is not necessary if it's self-explanatory."},"cellId":{"type":"string","description":"The ID for the code cell to execute. Avoid providing markdown cell IDs as nothing will be executed."},"continueOnError":{"type":"boolean","description":"Whether or not execution should continue for remaining cells if an error is encountered. Default to false unless instructed otherwise."}},"required":["filePath","cellId"]}},{"name":"run_vscode_command","description":"Run a command in VS Code. Use this tool to run a command in Visual Studio Code as part of a new workspace creation process only.","parameters":{"type":"object","properties":{"commandId":{"type":"string","description":"The ID of the command to execute. This should be in the format ."},"name":{"type":"string","description":"The name of the command to execute. This should be a clear and concise description of the command."},"args":{"type":"array","description":"The arguments to pass to the command. This should be an array of strings.","items":{"type":"string"}}},"required":["commandId","name"]}},{"name":"semantic_search","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.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The query to search the codebase for. Should contain all relevant context. Should ideally be text that might appear in the codebase, such as function names, variable names, or comments."}},"required":["query"]}},{"name":"test_failure","description":"Includes test failure information in the prompt.","parameters":{"type":"object","properties":{}}},{"name":"vscode_searchExtensions_internal","description":"This is a tool for browsing Visual Studio Code Extensions Marketplace. It allows the model to search for extensions and retrieve detailed information about them. The model should use this tool whenever it needs to discover extensions or resolve information about known ones. To use the tool, the model has to provide the category of the extensions, relevant search keywords, or known extension IDs. Note that search results may include false positives, so reviewing and filtering is recommended.","parameters":{"type":"object","properties":{"category":{"type":"string","description":"The category of extensions to search for","enum":["AI","Azure","Chat","Data Science","Debuggers","Extension Packs","Education","Formatters","Keymaps","Language Packs","Linters","Machine Learning","Notebooks","Programming Languages","SCM Providers","Snippets","Testing","Themes","Visualization","Other"]},"keywords":{"type":"array","items":{"type":"string"},"description":"The keywords to search for"},"ids":{"type":"array","items":{"type":"string"},"description":"The ids of the extensions to search for"}}}},{"name":"create_and_run_task","description":"Creates and runs a build, run, or custom task for the workspace by generating or adding to a tasks.json file based on the project structure (such as package.json or README.md). If the user asks to build, run, launch and they have no tasks.json file, use this tool. If they ask to create or add a task, use this tool.","parameters":{"type":"object","properties":{"workspaceFolder":{"type":"string","description":"The absolute path of the workspace folder where the tasks.json file will be created."},"task":{"type":"object","description":"The task to add to the new tasks.json file.","properties":{"label":{"type":"string","description":"The label of the task."},"type":{"type":"string","description":"The type of the task. The only supported value is 'shell'.","enum":["shell"]},"command":{"type":"string","description":"The shell command to run for the task. Use this to specify commands for building or running the application."},"args":{"type":"array","description":"The arguments to pass to the command.","items":{"type":"string"}},"isBackground":{"type":"boolean","description":"Whether the task runs in the background without blocking the UI or other tasks. Set to true for long-running processes like watch tasks or servers that should continue executing without requiring user attention. When false, the task will block the terminal until completion."},"problemMatcher":{"type":"array","description":"The problem matcher to use to parse task output for errors and warnings. Can be a predefined matcher like '$tsc' (TypeScript), '$eslint - stylish', '$gcc', etc., or a custom pattern defined in tasks.json. This helps VS Code display errors in the Problems panel and enables quick navigation to error locations.","items":{"type":"string"}},"group":{"type":"string","description":"The group to which the task belongs."}},"required":["label","type","command"]}},"required":["task","workspaceFolder"]}},{"name":"get_terminal_output","description":"Get the output of a terminal command previously started with run_in_terminal","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The ID of the terminal to check."}},"required":["id"]}},{"name":"manage_todo_list","description":"Manage a structured todo list to track progress and plan tasks throughout your coding session. Use this tool VERY frequently to ensure task visibility and proper planning.\n\nWhen to use this tool:\n- Complex multi-step work requiring planning and tracking\n- When user provides multiple tasks or requests (numbered/comma-separated)\n- After receiving new instructions that require multiple steps\n- BEFORE starting work on any todo (mark as in-progress)\n- IMMEDIATELY after completing each todo (mark completed individually)\n- When breaking down larger tasks into smaller actionable steps\n- To give users visibility into your progress and planning\n\nWhen NOT to use:\n- Single, trivial tasks that can be completed in one step\n- Purely conversational/informational requests\n- When just reading files or performing simple searches\n\nCRITICAL workflow:\n1. Plan tasks by writing todo list with specific, actionable items\n2. Mark ONE todo as in-progress before starting work\n3. Complete the work for that specific todo\n4. Mark that todo as completed IMMEDIATELY\n5. Move to next todo and repeat\n\nTodo states:\n- not-started: Todo not yet begun\n- in-progress: Currently working (limit ONE at a time)\n- completed: Finished successfully\n\nIMPORTANT: Mark todos completed as soon as they are done. Do not batch completions.","parameters":{"type":"object","properties":{"todoList":{"type":"array","description":"Complete array of all todo items (required for write operation, ignored for read). Must include ALL items - both existing and new.","items":{"type":"object","properties":{"id":{"type":"number","description":"Unique identifier for the todo. Use sequential numbers starting from 1."},"title":{"type":"string","description":"Concise action-oriented todo label (3-7 words). Displayed in UI."},"description":{"type":"string","description":"Detailed context, requirements, or implementation notes. Include file paths, specific methods, or acceptance criteria."},"status":{"type":"string","enum":["not-started","in-progress","completed"],"description":"not-started: Not begun | in-progress: Currently working (max 1) | completed: Fully finished with no blockers"}},"required":["id","title","description","status"]}},"operation":{"type":"string","enum":["write","read"],"description":"write: Replace entire todo list with new content. read: Retrieve current todo list. ALWAYS provide complete list when writing - partial updates not supported."}},"required":["operation"]}},{"name":"run_in_terminal","description":"This tool allows you to execute Windows PowerShell 5.1 commands in a persistent terminal session, preserving environment variables, working directory, and other context across multiple commands.\n\nCommand Execution:\n- Use semicolons ; to chain commands on one line, NEVER use && even when asked explicitly\n- Prefer pipelines | for object-based data flow\n- Never create a sub-shell (eg. powershell -c "command") unless explicitly asked\n\nDirectory Management:\n- Must use absolute paths to avoid navigation issues\n- Use $PWD or Get-Location for current directory\n- Use Push-Location/Pop-Location for directory stack\n\nProgram Execution:\n- Supports .NET, Python, Node.js, and other executables\n- Install modules via Install-Module, Install-Package\n- Use Get-Command to verify cmdlet/function availability\n\nBackground Processes:\n- For long-running tasks (e.g., servers), set isBackground=true\n- Returns a terminal ID for checking status and runtime later\n- Use Start-Job for background PowerShell jobs\n\nOutput Management:\n- Output is automatically truncated if longer than 60KB to prevent context overflow\n- Use Select-Object, Where-Object, Format-Table to filter output\n- Use -First/-Last parameters to limit results\n- For pager commands, add | Out-String or | Format-List\n\nBest Practices:\n- Use proper cmdlet names instead of aliases in scripts\n- Quote paths with spaces: "C:\Path With Spaces"\n- Prefer PowerShell cmdlets over external commands when available\n- Prefer idiomatic PowerShell like Get-ChildItem instead of dir or ls for file listings\n- Use Test-Path to check file/directory existence\n- Be specific with Select-Object properties to avoid excessive output","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The command to run in the terminal."},"explanation":{"type":"string","description":"A one-sentence description of what the command does. This will be shown to the user before the command is run."},"isBackground":{"type":"boolean","description":"Whether the command starts a background process. If true, the command will run in the background and you will not see the output. If false, the tool call will block on the command finishing, and then you will get the output. Examples of background processes: building in watch mode, starting a server. You can check the output of a background process later on by using get_terminal_output."}},"required":["command","explanation","isBackground"]}},{"name":"runSubagent","description":"Launch a new agent to handle complex, multi-step tasks autonomously. This tool is good at researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use this agent to perform the search for you.\n\n- Agents do not run async or in the background, you will wait for the agent's result.\n- When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.\n- Each agent invocation is stateless. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.\n- The agent's outputs should generally be trusted\n- Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n- If the user asks for a certain agent, you MUST provide that EXACT agent name (case-sensitive) to invoke that specific agent.","parameters":{"type":"object","properties":{"prompt":{"type":"string","description":"A detailed description of the task for the agent to perform"},"description":{"type":"string","description":"A short (3-5 word) description of the task"},"agentName":{"type":"string","description":"Optional name of a specific agent to invoke. If not provided, uses the current agent."}},"required":["prompt","description"]}},{"name":"terminal_last_command","description":"Get the last command run in the active terminal.","parameters":{"type":"object","properties":{}}},{"name":"terminal_selection","description":"Get the current selection in the active terminal.","parameters":{"type":"object","properties":{}}},{"name":"activate_pull_request_review_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is focused on managing pull request reviews within GitHub repositories. They allow users to add comments to pending reviews, create new reviews, submit existing pending reviews, and delete them if necessary. The tools facilitate collaboration by enabling reviewers to provide feedback on code changes before they are merged into the main branch. Users can create a new review or submit an existing one, ensuring that the review process is efficient and organized.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_repository_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis collection of tools is designed for comprehensive management of GitHub repositories. Users can create new repositories, branches, and pull requests, as well as create or update files and issues. The tools also allow for the addition of comments to issues and pull requests, enhancing communication among team members. By utilizing these tools, developers can effectively manage their codebase, track issues, and collaborate on changes, ensuring a smooth workflow in software development.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_repository_inspection_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group provides tools for inspecting various elements within a GitHub repository. Users can retrieve details about commits, file contents, labels, releases, and tags. These tools are essential for understanding the history and structure of a repository, allowing developers to analyze changes, track progress, and gather information about specific components. By leveraging these inspection tools, users can make informed decisions about code modifications and repository management.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_release_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis set of tools focuses on managing releases and tags within GitHub repositories. Users can list all releases, retrieve specific releases by tag name, and list all tags associated with a repository. These tools are crucial for version control and deployment processes, enabling developers to track software versions and manage updates effectively. By using these tools, teams can ensure that they are working with the correct versions of their software and can easily access historical releases.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_search_and_discovery_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is dedicated to searching and discovering various elements within GitHub. Users can search for code, repositories, and users, making it easier to locate specific projects, contributors, or code snippets. These tools enhance the ability to find relevant information quickly, whether for collaboration, research, or learning purposes. By utilizing these search capabilities, developers can efficiently navigate the vast ecosystem of GitHub and connect with the right resources.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_branch_and_commit_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis collection of tools is focused on managing branches and commits within GitHub repositories. Users can list all branches in a repository and retrieve a list of commits associated with a specific branch. These tools are essential for understanding the development history and current state of a project. By using these tools, developers can track changes, manage feature branches, and ensure that their work is organized and aligned with the overall project goals.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_pull_request_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is designed for managing pull requests within GitHub repositories. Users can list all pull requests, retrieve information about specific pull requests, search for pull requests using specific criteria, and update the branch of a pull request with the latest changes. These tools facilitate the review and integration of code changes, ensuring that contributions are properly evaluated and merged into the main codebase. By utilizing these tools, teams can streamline their code review process and maintain high-quality standards.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"mcp_io_github_git_assign_copilot_to_issue","description":"Assign Copilot to a specific issue in a GitHub repository.\n\nThis tool can help with the following outcomes:\n- a Pull Request created with source code changes to resolve the issue\n\n\nMore information can be found at:\n- https://docs.github.com/en/copilot/using-github-copilot/using-copilot-coding-agent-to-work-on-tasks/about-assigning-tasks-to-copilot\n","parameters":{"type":"object","required":["owner","repo","issueNumber"],"properties":{"issueNumber":{"type":"number","description":"Issue number"},"owner":{"type":"string","description":"Repository owner"},"repo":{"type":"string","description":"Repository name"}}}},{"name":"mcp_io_github_git_delete_file","description":"Delete a file from a GitHub repository","parameters":{"type":"object","required":["owner","repo","path","message","branch"],"properties":{"branch":{"type":"string","description":"Branch to delete the file from"},"message":{"type":"string","description":"Commit message"},"owner":{"type":"string","description":"Repository owner (username or organization)"},"path":{"type":"string","description":"Path to the file to delete"},"repo":{"type":"string","description":"Repository name"}}}},{"name":"mcp_io_github_git_fork_repository","description":"Fork a GitHub repository to your account or specified organization","parameters":{"type":"object","required":["owner","repo"],"properties":{"organization":{"type":"string","description":"Organization to fork to"},"owner":{"type":"string","description":"Repository owner"},"repo":{"type":"string","description":"Repository name"}}}},{"name":"mcp_io_github_git_get_teams","description":"Get details of the teams the user is a member of. Limited to organizations accessible with current credentials","parameters":{"type":"object","properties":{"user":{"type":"string","description":"Username to get teams for. If not provided, uses the authenticated user."}}}},{"name":"mcp_io_github_git_list_issue_types","description":"List supported issue types for repository owner (organization).","parameters":{"type":"object","required":["owner"],"properties":{"owner":{"type":"string","description":"The organization owner of the repository"}}}},{"name":"mcp_io_github_git_list_issues","description":"List issues in a GitHub repository. For pagination, use the 'endCursor' from the previous response's 'pageInfo' in the 'after' parameter.","parameters":{"type":"object","required":["owner","repo"],"properties":{"after":{"type":"string","description":"Cursor for pagination. Use the endCursor from the previous page's PageInfo for GraphQL APIs."},"direction":{"type":"string","description":"Order direction. If provided, the 'orderBy' also needs to be provided.","enum":["ASC","DESC"]},"labels":{"type":"array","description":"Filter by labels","items":{"type":"string"}},"orderBy":{"type":"string","description":"Order issues by field. If provided, the 'direction' also needs to be provided.","enum":["CREATED_AT","UPDATED_AT","COMMENTS"]},"owner":{"type":"string","description":"Repository owner"},"perPage":{"type":"number","description":"Results per page for pagination (min 1, max 100)","minimum":1,"maximum":100},"repo":{"type":"string","description":"Repository name"},"since":{"type":"string","description":"Filter by date (ISO 8601 timestamp)"},"state":{"type":"string","description":"Filter by state, by default both open and closed issues are returned when not provided","enum":["OPEN","CLOSED"]}}}},{"name":"mcp_io_github_git_push_files","description":"Push multiple files to a GitHub repository in a single commit","parameters":{"type":"object","required":["owner","repo","branch","files","message"],"properties":{"branch":{"type":"string","description":"Branch to push to"},"files":{"type":"array","description":"Array of file objects to push, each object with path (string) and content (string)","items":{"type":"object","required":["path","content"],"properties":{"content":{"type":"string","description":"file content"},"path":{"type":"string","description":"path to the file"}}}},"message":{"type":"string","description":"Commit message"},"owner":{"type":"string","description":"Repository owner"},"repo":{"type":"string","description":"Repository name"}}}},{"name":"mcp_io_github_git_request_copilot_review","description":"Request a GitHub Copilot code review for a pull request. Use this for automated feedback on pull requests, usually before requesting a human reviewer.","parameters":{"type":"object","required":["owner","repo","pullNumber"],"properties":{"owner":{"type":"string","description":"Repository owner"},"pullNumber":{"type":"number","description":"Pull request number"},"repo":{"type":"string","description":"Repository name"}}}},{"name":"activate_observation_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is focused on managing observations within a knowledge graph. The 'Add new observations to existing entities in the knowledge graph' tool allows users to enrich existing entities with additional data, enhancing the depth and utility of the knowledge graph. Conversely, the 'Delete specific observations from entities in the knowledge graph' tool provides the capability to remove outdated or incorrect observations, ensuring that the knowledge graph remains accurate and relevant. Together, these tools enable users to maintain the integrity and richness of the knowledge graph by facilitating both the addition and removal of observations as needed.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_entity_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group encompasses tools designed for the creation and deletion of entities and their relationships within a knowledge graph. The 'Create multiple new entities in the knowledge graph' tool allows users to efficiently add new entities, expanding the graph's scope and potential insights. On the other hand, the 'Delete multiple entities and their associated relations from the knowledge graph' tool enables users to remove entities that are no longer relevant, along with their connections, thereby streamlining the graph. Additionally, the 'Delete multiple relations from the knowledge graph' tool allows for targeted removal of specific relationships, providing fine-grained control over the graph's structure. Collectively, these tools empower users to effectively manage the lifecycle of entities and their interconnections within the knowledge graph.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_node_access_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group consists of tools that facilitate access to specific nodes within a knowledge graph. The 'Open specific nodes in the knowledge graph by their names' tool allows users to directly access and view detailed information about particular nodes, making it easier to navigate the graph. Meanwhile, the 'Search for nodes in the knowledge graph based on a query' tool provides a powerful search capability, enabling users to find nodes that match specific criteria or keywords. Together, these tools enhance user interaction with the knowledge graph by simplifying the process of locating and accessing relevant nodes, thereby improving the overall usability and efficiency of knowledge exploration.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"mcp_memory_create_relations","description":"Create multiple new relations between entities in the knowledge graph. Relations should be in active voice","parameters":{"type":"object","properties":{"relations":{"type":"array","items":{"type":"object","properties":{"from":{"description":"The name of the entity where the relation starts","type":"string"},"to":{"description":"The name of the entity where the relation ends","type":"string"},"relationType":{"description":"The type of the relation","type":"string"}},"required":["from","to","relationType"]}}},"required":["relations"]}},{"name":"mcp_memory_read_graph","description":"Read the entire knowledge graph","parameters":{"type":"object","properties":{}}},{"name":"activate_web_browser_interaction_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group of tools is designed to facilitate various interactions with web browsers, enabling automated navigation and manipulation of web pages. Each tool serves a specific function that contributes to a seamless browsing experience, making it ideal for tasks such as web scraping, automated testing, or user simulation. \n\nThe tools include functionalities for performing clicks on web elements, handling dialog boxes, and navigating to specific URLs. This allows users to automate the process of interacting with web applications, which can be particularly useful for testing user interfaces or gathering data from websites. \n\nAdditionally, the ability to hover over elements and select options from dropdown menus enhances the capability to interact with dynamic web content. Users can simulate user behavior more accurately, which is essential for testing scenarios where user input is required. \n\nThe tools also provide options for keyboard interactions, such as pressing keys and typing text into editable fields, which further expands the range of automated tasks that can be performed. This is particularly useful for filling out forms or executing keyboard shortcuts within web applications. \n\nFinally, the ability to resize the browser window and navigate back to previous pages adds flexibility to the automation process, allowing users to create more complex workflows that mimic real user behavior. Together, these tools create a robust suite for automating web interactions, enhancing productivity and efficiency in web-based tasks.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_form_and_file_management_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group focuses on managing forms and file uploads within web applications. The tools included allow users to fill out multiple form fields efficiently, which is essential for automating data entry tasks in scenarios such as user registration, surveys, or any application requiring user input. By automating the filling of forms, users can save time and reduce the likelihood of errors associated with manual entry.\n\nIn addition to form filling, the tools also provide capabilities for uploading one or multiple files. This is particularly useful in applications where users need to submit documents, images, or other files as part of their interaction with the web service. The ability to automate file uploads can significantly enhance user experience and streamline processes that involve document submission.\n\nTogether, these tools enable comprehensive management of user input and file handling in web applications. They can be utilized in testing environments to simulate user behavior or in production environments to automate repetitive tasks, ensuring that data is entered accurately and efficiently. This combination of form and file management capabilities is crucial for developers and testers looking to enhance their web application workflows.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"activate_web_page_capture_tools","description":"Call this tool when you need access to a new category of tools. The category of tools is described as follows:\n\nThis group consists of tools designed for capturing visual representations of web pages, specifically focusing on accessibility and standard screenshots. The 'mcp_microsoft_pla_browser_snapshot' tool allows users to capture an accessibility snapshot of the current page, which is more informative than a traditional screenshot as it provides insights into the page's accessibility features. This is particularly useful for developers and designers who need to ensure their web content is accessible to all users, including those with disabilities.\n\nOn the other hand, the 'mcp_microsoft_pla_browser_take_screenshot' tool enables users to take a standard screenshot of the current page. While this tool is straightforward and captures the visual layout of the page, it does not provide the interactive capabilities that the accessibility snapshot offers. Users can utilize this tool for quick visual documentation or sharing of the page's appearance.\n\nTogether, these tools can be used in a complementary manner. For instance, a web developer might first take an accessibility snapshot to evaluate how well the page meets accessibility standards and then follow up with a screenshot to document the visual design for stakeholders. This dual approach ensures that both functional and aesthetic aspects of the web page are considered.\n\nThese tools are particularly valuable in web development and design workflows, where understanding both the visual and functional accessibility of a page is crucial. By integrating these tools into their processes, teams can enhance their ability to create inclusive and user-friendly web experiences.\n\nOverall, the web_page_capture_tools group provides essential functionalities for capturing and analyzing web pages, making them indispensable for anyone involved in web development, design, or accessibility auditing.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}},{"name":"mcp_microsoft_pla_browser_console_messages","description":"Returns all console messages","parameters":{"type":"object","properties":{"level":{"type":"string","enum":["error","warning","info","debug"],"default":"info","description":"Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info"."}},"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_drag","description":"Perform drag and drop between two elements","parameters":{"type":"object","properties":{"startElement":{"type":"string","description":"Human-readable source element description used to obtain the permission to interact with the element"},"startRef":{"type":"string","description":"Exact source element reference from the page snapshot"},"endElement":{"type":"string","description":"Human-readable target element description used to obtain the permission to interact with the element"},"endRef":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["startElement","startRef","endElement","endRef"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_evaluate","description":"Evaluate JavaScript expression on page or element","parameters":{"type":"object","properties":{"function":{"type":"string","description":"() => { / code / } or (element) => { / code */ } when element is provided"},"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["function"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_install","description":"Install the browser specified in the config. Call this if you get an error about the browser not being installed.","parameters":{"type":"object","properties":{},"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_network_requests","description":"Returns all network requests since loading the page","parameters":{"type":"object","properties":{"includeStatic":{"type":"boolean","default":false,"description":"Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false."}},"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_run_code","description":"Run Playwright code snippet","parameters":{"type":"object","properties":{"code":{"type":"string","description":"A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }"}},"required":["code"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_tabs","description":"List, create, close, or select a browser tab.","parameters":{"type":"object","properties":{"action":{"type":"string","enum":["list","new","close","select"],"description":"Operation to perform"},"index":{"type":"number","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_wait_for","description":"Wait for text to appear or disappear or a specified time to pass","parameters":{"type":"object","properties":{"time":{"type":"number","description":"The time to wait in seconds"},"text":{"type":"string","description":"The text to wait for"},"textGone":{"type":"string","description":"The text to wait for to disappear"}},"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_navigate","description":"Navigate to a URL","parameters":{"type":"object","properties":{"url":{"type":"string","description":"The URL to navigate to"}},"required":["url"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_navigate_back","description":"Go back to the previous page","parameters":{"type":"object","properties":{},"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_handle_dialog","description":"Handle a dialog","parameters":{"type":"object","properties":{"accept":{"type":"boolean","description":"Whether to accept the dialog."},"promptText":{"type":"string","description":"The text of the prompt in case of a prompt dialog."}},"required":["accept"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_close","description":"Close the page","parameters":{"type":"object","properties":{},"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_select_option","description":"Select an option in a dropdown","parameters":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"values":{"type":"array","items":{"type":"string"},"description":"Array of values to select in the dropdown. This can be a single value or multiple values."}},"required":["element","ref","values"],"additionalProperties":false}},{"name":"mcp_microsoft_pla_browser_type","description":"Type text into editable element","parameters":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"text":{"type":"string","description":"Text to type into the element"},"submit":{"type":"boolean","description":"Whether to submit entered text (press Enter after)"},"slowly":{"type":"boolean","description":"Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once."}},"required":["element","ref","text"],"additionalProperties":false}}]}],"sessionId":"-820634454806834268","toolConfig":{"functionCallingConfig":{"mode":"VALIDATED"}}},"model":"claude-sonnet-4-5","userAgent":"antigravity","requestId":"agent-b0313317-17c5-48e9-a048-3809a0d0f605"}

=== API RESPONSE ===
{
"error": {
"code": 400,
"message": "{"type":"error","error":{"type":"invalid_request_error","message":"messages.3.content.0.tool_use.id: String should match pattern '^[a-zA-Z0-9_-]+$'"},"request_id":"req_vrtx_011CWC66JdZ4zEgoGsShm311"}",
"status": "INVALID_ARGUMENT"
}
}

=== RESPONSE ===
Status: 400
Access-Control-Allow-Origin: *
Access-Control-Allow-Methods: GET, POST, PUT, PATCH, DELETE, OPTIONS
Access-Control-Allow-Headers: *
Content-Type: application/json
Cache-Control: no-cache
Connection: keep-alive

{
"error": {
"code": 400,
"message": "{"type":"error","error":{"type":"invalid_request_error","message":"messages.3.content.0.tool_use.id: String should match pattern '^[a-zA-Z0-9_-]+$'"},"request_id":"req_vrtx_011CWC66JdZ4zEgoGsShm311"}",
"status": "INVALID_ARGUMENT"
}
}

[luispater]

Which client do you use?