agentrouter problem

[ahmedrageh]

https://agentrouter.org/v1 -> codex base url
http://localhost:8317/v1/chat/completions -> cliproxy

response -> 500 -> auth_unavailable: no auth available

[luispater]

1. Set the request-log: true in your config.yaml.
2. Request again.
3. Attach your config.yaml here.
4. Attach your request log here.

The information you provided is not enough.

[ahmedrageh]

when use kilo code is work
but another not work

=== REQUEST INFO ===
URL: /v1/chat/completions
Method: POST
Timestamp: 2025-11-09T20:58:47.2229622+03:00

=== HEADERS ===
Content-Length: 98183
Content-Type: application/json
Accept-Language: *
Authorization: Bearer sk-v...PxX2
Accept: /
Sec-Fetch-Mode: cors
Connection: keep-alive
User-Agent: oai-compatible-copilot/0.1.4 VSCode/1.106.0-insider
Accept-Encoding: gzip, deflate

=== REQUEST BODY ===
{"model":"gpt-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 gpt-5::thinking via agentrouter.\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\nTo edit files in the workspace, use the apply_patch tool. If you have issues with it, you should first try to fix your patch and continue using apply_patch. \nThe input for this tool is a string representing the patch to apply, following a special format. For each snippet of code that needs to be changed, repeat the following:\n*** Update File: [file_path]\n[context_before] -> See below for further instructions on context.\n-[old_code] -> Precede each line in the old code with a minus sign.\n+[new_code] -> Precede each line in the new, replacement code with a plus sign.\n[context_after] -> See below for further instructions on context.\n\nFor instructions on [context_before] and [context_after]:\n- By default, show 3 lines of code immediately above and 3 lines immediately below each change. If a change is within 3 lines of a previous change, do NOT duplicate the first change's [context_after] lines in the second change's [context_before] lines.\n- If 3 lines of context is insufficient to uniquely identify the snippet of code within the file, use the @@ operator to indicate the class or function to which the snippet belongs.\n- If a code block is repeated so many times in a class or function such that even a single @@ statement and 3 lines of context cannot uniquely identify the snippet of code, you can use multiple @@ statements to jump to the right context.\nYou must use the same indentation style as the original code. If the original code uses tabs, you must use tabs. If the original code uses spaces, you must use spaces. Be sure to use a proper UNESCAPED tab character.\n\nSee below for an example of the patch format. If you propose changes to multiple regions in the same file, you should repeat the *** Update File header for each snippet of code to change:\n\n*** Begin Patch\n*** Update File: /Users/someone/pygorithm/searching/binary_search.py\n@@ class BaseClass\n@@ def method():\n[3 lines of pre-context]\n-[old_code]\n+[new_code]\n+[new_code]\n[3 lines of post-context]\n*** End Patch\n\nNEVER print this out to the user, instead call the tool and the edits will be applied and shown to the user.\nFollow best practices when editing files. If a popular external library exists to solve a problem, use it and properly install the package e.g. with "npm install" or creating a "requirements.txt".\nIf you're building a webapp from scratch, give it a beautiful and modern UI.\nAfter editing a file, any new errors in the file will be in the tool result. Fix the errors if they are relevant to your change or the prompt, and if you can figure out how to fix them, and remember to validate that they were actually fixed. Do not loop more than 3 times attempting to fix errors in the same file. If the third try fails, you should stop and ask the user what to do next.\n\n\n<instruction forToolsWithPrefix="mcp_upstash">\nUse this server to retrieve up-to-date documentation and code examples for any library.\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\nHere is a list of instruction files that contain rules for modifying or creating new code.\nThese files are important for ensuring that the code is modified or created correctly.\nPlease make sure to follow the rules specified in these files when working with the codebase.\nIf the file is not already available as attachment, use the read_file tool to acquire it.\nMake sure to acquire the instructions before making any changes to the code.\n| File | Applies To | Description |\n| ------- | --------- | ----------- |\n| 'd:\Share\HailEmp\.github\instructions\ExecutiveOffice.instructions.md' | / | |\n| 'd:\Share\HailEmp\.github\instructions\rules.instructions.md' | / | |\n<attachment filePath="d:\\Share\\HailEmp\\AGENTS.md">\n---\r\n# --- بيانات تعريف الوكيل (للاستخدام من قبل المحرر والأنظمة الذكية) ---\r\nname: "وكيل مشروع أمانة منطقة حائل"\r\ndescription: "وكيل ذكي متخصص في تطوير وصيانة وتوثيق مشروع بوابة موظفي أمانة منطقة حائل (amanathail.gov.sa/Emp/). الالتزام الصارم بالقواعد المحددة إلزامي. جميع الردود والتعاملات يجب أن تكون باللغة العربية."\r\nversion: "1.0.0"\r\n\r\n# --- السياق التقني للمشروع ---\r\ncontext:\r\n framework: "CodeIgniter 3.1.4"\r\n language: "PHP 5.6"\r\n database_driver: "mysqli"\r\n database_config:\r\n pconnect: false\r\n environment_url: "https://amanathail.gov.sa/Emp/"\r\n prohibited_technologies: ["Node.js"]\r\n database_access:\r\n tool: "mysql"\r\n password: "1234"\r\n\r\n# --- قواعد العمل الإلزامية ---\r\nrules:\r\n - id: "coding_standards"\r\n description: "الالتزام الصارم بمعايير التسمية والهيكلية الخاصة بـ CodeIgniter."\r\n details:\r\n controllers: "الاسم يبدأ بحرف كبير ويطابق اسم الملف (مثال: Employees.php يحتوي على class Employees)."\r\n models: "اسم الملف والصف ينتهيان بـ _model (مثال: Employee_model.php يحتوي على class Employee_model)."\r\n methods: "أسماء عربية/إنجليزية واضحة بأسلوب snake_case للطرق العامة."\r\n comments: "إضافة تعليقات توضيحية باللغة العربية للدوال والملفات المهمة."\r\n core_extension: "استخدام MY_Controller في application/core للمهام المشتركة."\r\n\r\n - id: "ui_ux_policy"\r\n description: "يجب أن تتبع جميع الواجهات قانون جاكوب (Jakob's Law) والمرجع التصميمي الرسمي."\r\n details:\r\n principle: "يجب أن تكون الواجهة مألوفة، بسيطة، وتعمل كما يتوقع المستخدم."\r\n reference_file: "documentation/design_reference.md"\r\n update_protocol: "عند ابتكار مكونات جديدة، يجب توثيقها في هذا الملف مع ضمان اتساقها مع الهوية البصرية."\r\n\r\n - id: "testing_deployment"\r\n description: "الاختبار يتم مباشرة على بيئة الإنتاج وفق بروتوكول محدد."\r\n details:\r\n test_files_location: "يتم إنشاء الملفات الاختبارية داخل مجلد public."\r\n session_init_url: "https://amanathail.gov.sa/Emp/login/LogINAdminHa1l25584863157aDmjuEUI"\r\n development_mode_trigger: "?development"\r\n automation_tool: "Playwright MCP"\r\n deployment_delay_seconds: 30\r\n\r\n - id: "documentation_policy"\r\n description: "الحفاظ على تحديث التوثيق بشكل فوري بعد كل تغيير."\r\n details:\r\n root_folder: "documentation/"\r\n overview_file: "documentation/MAIN_SERVICES_OVERVIEW.md"\r\n service_guide_pattern: "documentation/{service_name}/{SERVICE_NAME}_COMPLETE_GUIDE.md"\r\n\r\n - id: "security_mandates"\r\n description: "الالتزام الصارم ببروتوكولات الأمان لحماية النظام."\r\n details:\r\n sql_injection_prevention: ["Query Builder", "Data Binding"]\r\n xss_csrf_protection:\r\n - "تفعيل csrf_protection = TRUE في config.php."\r\n - "استخدام xss_clean لنقاط الإدخال الحساسة."\r\n session_management: "إدارة الجلسات وفق الإعدادات المعتمدة في config.php."\r\n\r\n - id: "integrated_services_management"\r\n description: "إدارة الخدمات المدمجة وضمان عدم كسر التكامل بينها."\r\n details:\r\n identification: "يتم تحديد الخدمة الحالية من خلال مسار الملفات أو السياق المقدم."\r\n integration_check: "تأكد من أن أي تغيير لا يكسر التكامل بين الوحدات المختلفة."\r\n\r\n# --- قاعدة المعرفة والمراجع ---\r\nknowledge_base:\r\n design_reference: "documentation/design_reference.md"\r\n services_overview: "documentation/MAIN_SERVICES_OVERVIEW.md"\r\n service_guides_pattern: "documentation/{service_name}/{SERVICE_NAME}_COMPLETE_GUIDE.md"\r\n\r\n# --- الأدوات المستخدمة ---\r\ntools:\r\n automation: "Playwright MCP"\r\n database_cli: "mysql"\r\n---\r\n# وكيل مشروع أمانة منطقة حائل (amanathail.gov.sa/Emp/)\r\n\r\n> هذا المستند هو المرجع التقني الشامل لتطوير وصيانة المشروع. يجب الالتزام الصارم بهذه القواعد في جميع مراحل العمل. ملاحظة هامة: جميع الردود والتعاملات والاكواد التي يتم إنشاؤها يجب أن تكون باللغة العربية.\r\n\r\n---\r\n\r\n## 1. البيئة والمكدس التقني (Environment & Tech Stack)\r\n\r\n الإطار: CodeIgniter 3.1.4\r\n اللغة: PHP 5.6\r\n* قاعدة البيانات: mysqli (مع pconnect = FALSE)\r\n* بيئة الإنتاج والاختبار: https://amanathail.gov.sa/Emp/\r\n* قيود: يُمنع استخدام Node.js في بيئة الإنتاج.\r\n* الوصول المباشر لقاعدة البيانات: يمكن استخدام أمر mysql من الطرفية عند الحاجة.\r\n * كلمة المرور: 1234\r\n\r\n---\r\n\r\n## 2. معايير الكود والتسمية (Coding & Naming Standards)\r\n\r\n* الهيكلية: اتباع الهيكل القياسي لـ CodeIgniter.\r\n* التسمية:\r\n * Controllers: الاسم يبدأ بحرف كبير ويطابق اسم الملف (مثال: Employees.php يحتوي على class Employees).\r\n * Models: اسم الملف والصف ينتهيان بـ _model (مثال: Employee_model.php يحتوي على class Employee_model).\r\n * الدوال: أسماء عربية/إنجليزية واضحة بأسلوب snake_case للطرق العامة.\r\n* التعليقات: إضافة تعليقات توضيحية باللغة العربية للدوال والملفات المهمة.\r\n* الأساس (Core): استخدام MY_Controller في application/core للمهام المشتركة (فحص الجلسة، تحميل اللغات، تهيئة الأمان).\r\n\r\n---\r\n\r\n## 3. سياسة التصميم وواجهة المستخدم (UI/UX & Design Policy)\r\n\r\n* القانون الأساسي: يجب أن تتبع جميع الواجهات قانون جاكوب (Jakob's Law). يجب أن تكون الواجهة مألوفة، بسيطة، وتعمل كما يتوقع المستخدم.\r\n* المرجع التصميمي:\r\n * المصدر: documentation\\design_reference.md.\r\n * الاستخدام: يجب اعتماد المكونات والأنماط من هذا الملف كأساس لأي تصميم جديد.\r\n * التحديث: عند ابتكار مكونات جديدة، يجب توثيقها في هذا الملف مع ضمان اتساقها مع الهوية البصرية.\r\n\r\n---\r\n\r\n## 4. بروتوكول الاختبار والإطلاق (Testing & Deployment Protocol)\r\n\r\n* موقع الملفات الاختبارية: يتم إنشاء الملفات الاختبارية داخل مجلد public حيث يمكن تنفيذ ملفات PHP مباشرة.\r\n* البيئة: يتم الاختبار مباشرة على بيئة الإنتاج لضمان التوافق الكامل. لا يُعتمد على البيئات المحلية.\r\n* خطوات الاختبار الإلزامية:\r\n 1. تهيئة الجلسة: قبل بدء أي اختبار، يجب زيارة صفحة الدخول لإنشاء جلسة صالحة:\r\n https://amanathail.gov.sa/Emp/login/LogINAdminHa1l25584863157aDmjuEUI\r\n 2. اختبار الميزات الجديدة: لاختبار صفحة أو ميزة جديدة، أضف ?development إلى الرابط.\r\n (مثال: https://amanathail.gov.sa/Emp/policies?development)\r\n 3. التحقق: اقرأ محتوى الصفحة وتأكد من عدم وجود أخطاء قبل المتابعة.\r\n* الأتمتة: استخدم Playwright MCP لإجراء الاختبارات الآلية.\r\n* ملاحظة هامة: قد تتأخر التحديثات في الظهور على السيرفر لمدة تصل إلى 30 ثانية.\r\n\r\n---\r\n\r\n## 5. سياسة التوثيق وإدارة المعرفة (Documentation & Knowledge Mngmt)\r\n\r\n* الهيكل العام:\r\n * المجلد الرئيسي: documentation/.\r\n * نظرة عامة: ملف MAIN_SERVICES_OVERVIEW.md يحتوي على نظرة عامة على جميع الخدمات.\r\n * توثيق الخدمات: لكل خدمة مجلد خاص بها (مثال: documentation/security_safety/).\r\n * الدليل الشامل: داخل كل مجلد خدمة، يجب وجود ملف SERVICE_NAME_COMPLETE_GUIDE.md.\r\n* التحديث: يجب تحديث التوثيق بشكل فوري بعد كل تغيير مهم.\r\n* إدارة المعرفة: يجب حفظ المعلومات والتحديات والحلول المهمة في الذاكرة وتوثيقها.\r\n\r\n---\r\n\r\n## 6. قواعد الأمان (Security Rules)\r\n\r\n* حقن SQL: استخدم Query Builder و Data Binding بشكل إلزامي لمنع هجمات حقن SQL.\r\n* الحماية من XSS/CSRF:\r\n * تفعيل csrf_protection = TRUE في config.php.\r\n * استخدام xss_clean لنقاط الإدخال الحساسة.\r\n* الجلسات: إدارة الجلسات وفق الإعدادات المعتمدة في config.php (sess_driver, sess_save_path).\r\n\r\n---\r\n\r\n## 7. إدارة الخدمات المدمجة (Integrated Services Management)\r\n\r\n* التعريف: المشروع عبارة عن نظام مدمج يحتوي على عدة خدمات متكاملة.\r\n* تحديد الخدمة: يتم تحديد الخدمة التي يتم العمل عليها من خلال:\r\n * مسار الملفات التي يتم تعديلها.\r\n * السياق المقدم في التعليمات.\r\n * مجلد التوثيق الخاص بالخدمة (مثال: documentation/security_safety/).\r\n* التكامل: تأكد من أن أي تغيير لا يكسر التكامل بين الوحدات المختلفة.\r\n\r\n---\r\n\r\n## 8. تعليمات السياق للذكاء الاصطناعي (AI Instruction Context)\r\n\r\nهذا القسم موجّه لأنظمة الذكاء الاصطناعي (مثل ChatGPT أو أدوات MCP) للمساعدة في تطوير المشروع وفق القواعد التقنية الرسمية.\r\n\r\n* تحديد الخدمة الحالية: قبل تنفيذ أي تعديل أو إنشاء ملف جديد، يجب أن يتعرف النظام على الخدمة النشطة من خلال مسار الملفات أو السياق المقدم.\r\n* الرجوع إلى التوثيق: عند الحاجة إلى مرجع أو تحديث، يجب الرجوع إلى مجلد التوثيق الخاص بالخدمة داخل documentation/ (مثل documentation/security_safety/).\r\n* تحديث المعرفة: في حال إضافة أو تعديل ميزة، يجب تعديل ملف التوثيق الخاص بها مباشرة بعد الانتهاء.\r\n* التوافق: يجب على الذكاء الاصطناعي التأكد من أن أي تعديل متوافق مع بيئة PHP 5.6 و CodeIgniter 3.1.4.\r\n* اختبار التنفيذ: يمكن إنشاء ملفات اختبار في مجلد public/ والتحقق من عملها عبر روابط مباشرة.\r\n* أوامر قاعدة البيانات: يمكن تنفيذ أوامر mysql من الطرفية (كلمة المرور: 1234) عند الحاجة لأغراض الصيانة أو الاختبار.\r\n* اللغة: يجب أن تكون جميع الردود، الشرح، وأسماء المتغيرات والدوال الجديدة باللغة العربية قدر الإمكان، مع الحفاظ على التوافق التقني.\r\n\r\n---\n\n\n\n"},{"role":"user","content":"<environment_info>\nThe user's current OS is: Windows\nThe user's default shell is: "powershell.exe" (Windows PowerShell v5.1). When you generate terminal commands, please generate them correctly for this shell. Use the ; character if joining commands on a single line is needed.\n</environment_info>\n<workspace_info>\nThe following tasks can be executed using the run_task tool if they are not already running:\n<workspaceFolder path="d:\\Share\\HailEmp">\n<task id="shell: اختبار إصلاحات لوحة الدفعات">\n{\n\t"label": "اختبار إصلاحات لوحة الدفعات",\n\t"type": "shell",\n\t"command": "php",\n\t"args": [\n\t\t"-S",\n\t\t"localhost:8080",\n\t\t"-t",\n\t\t"."\n\t],\n\t"group": "test",\n\t"isBackground": true\n}\n\n<task id="shell: اختبار حالة قاعدة البيانات - إبرام">\n{\n\t"label": "اختبار حالة قاعدة البيانات - إبرام",\n\t"type": "shell",\n\t"command": "php",\n\t"args": [\n\t\t"-S",\n\t\t"localhost:8081",\n\t\t"-t",\n\t\t".",\n\t\t"test_database_status.php"\n\t],\n\t"group": "test",\n\t"isBackground": true\n}\n\n<task id="shell: تشغيل نظام إبرام">\n{\n\t"label": "تشغيل نظام إبرام",\n\t"type": "shell",\n\t"command": "php",\n\t"args": [\n\t\t"-S",\n\t\t"localhost:8082",\n\t\t"-t",\n\t\t"."\n\t],\n\t"group": "build",\n\t"isBackground": true\n}\n\n<task id="shell: Check permit table structure">\n{\n\t"label": "Check permit table structure",\n\t"type": "shell",\n\t"command": "php",\n\t"args": [\n\t\t"-S",\n\t\t"localhost:8083",\n\t\t"-t",\n\t\t"."\n\t],\n\t"isBackground": true,\n\t"group": "build"\n}\n\n\n\nI am working in a workspace with the following folders:\n- d:\Share\HailEmp \nI am working in a workspace that has the following structure:\n\nadd_applicant_documents_fields.sql\nadd_education_fields_to_applicants.sql\nadd_interview_and_conversion_fields_to_applications.sql\nadd_monthly_salary_to_opportunities.sql\nadd_password_reset_columns.sql\nadd_required_profile_fields.sql\nadd_simple_evaluation_fields.sql\nADD_SMART_NOTIFICATIONS_COLUMN.sql\nadd_supervisor_table.sql\nADD_TASK_PAGE_TEST_REPORT.md\nadd_token_expires_at_column.sql\nAGENTS.md\nAPI_ENDPOINTS_VERIFICATION.md\nAPPLICANT_DOCUMENTS_FEATURE_REPORT.md\nAPPLICATION_DETAILS_DESIGN_IMPROVEMENT_REPORT.md\nAPPLICATION_STATUS_DISPLAY_FIX_REPORT.md\nATTACHMENTS_FIX_REPORT.md\nAUTH_UNIFIED_LIBRARY_FIX_REPORT.md\nBUG_FIXES_SUMMARY.md\nBUTTON_LOADER_ENHANCEMENT.md\nCACHE_FIX_SUMMARY.md\nCHANGELOG.md\ncheck_applicants_fields.php\ncheck_applicants_table.php\ncheck_application_1.php\ncheck_data.php\ncheck_db_tables.php\ncheck_images_37.sql\ncheck_interview_evaluations_table.php\ncheck_new_fields.php\ncheck_recommendations.php\ncheck_session_106_logs.php\ncheck_session_106.php\ncheck_tables.php\ncheck_tamheer_applicants_structure.php\ncheck_tamheer_tables.php\ncheck_user_data.php\ncheck_users_table.php\ncheck_vehicles_table.php\nCOMMENT_1_IMPLEMENTATION_REPORT.md\nCOMMENT_8_IMPLEMENTATION_SUMMARY.md\nCOMPLETE_CACHE_FIX_REPORT.md\nCOMPLETE_SUCCESS_REPORT.md\nCOMPREHENSIVE_SUCCESS_REPORT.md\ncopy_files_to_server.ps1\nCORRECT_IMPLEMENTATION.md\nCORS_FIX_COMPLETE_REPORT.md\ncreate_table_and_data.sql\ncreate_test_user.sql\nDATABASE_CONNECTION_FIX_REPORT.md\nDATABASE_CREATION_FINAL_REPORT.md\nDATABASE_CREATION_REPORT.md\nDATABASE_ERROR_FIX_REPORT.md\ndebug_csrf_token.php\ndebug_database_data.php\ndebug_save_recommendation.php\ndebug_sessions.php\nDEPLOYMENT_GUIDE.md\nDEPLOYMENT_INSTRUCTIONS.md\nDEVELOPMENT_MODE_FIX_REPORT.md\nDISPLAY_FIXES_SUMMARY.md\nDUAL_STATUS_CARD_FIX_REPORT.md\nEDIT_OPPORTUNITY_FUNCTIONALITY_COMPLETE_TEST_REPORT.md\nENHANCEMENTS_SUMMARY.md\nEXCESSIVE_CODE_AUDIT_REPORT.md\nEXECUTION_FIELDS_IMPLEMENTATION.md\nFINAL_CACHE_FIX_IMPLEMENTATION_REPORT.md\nFINAL_DATABASE_FIX.md\nFINAL_FIX_REPORT.md\n...\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 November 9, 2025.\nTerminals:\nTerminal: Codex - Install WSL\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: اختبار إصلاحات لوحة الدفعات\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nTerminal: powershell\nLast Command: cd d:\Share\HailEmp\application\views\Tamheer\Supervisor ; cp application_details.php application_details_backup.php\nCwd: D:\Share\HailEmp\nExit Code: 0\n\n\n\nThe user's current file is vscode-userdata:/c%3A/Users/Ahmed%20Rageh/AppData/Roaming/Code%20-%20Insiders/User/settings.json. \n\n\nBelow is the information about the current repository. You can use this information when you need to calculate diffs or compare changes with the default branch.\nRepository name: HailEmp\nOwner: ahmedrageh\nCurrent branch: main\n\n\n\n\n\n\nhi\n\n"}],"stream":true,"stream_options":{"include_usage":true},"temperature":0.7,"top_p":1,"thinking":{"type":"enabled"},"tools":[{"type":"function","function":{"name":"apply_patch","description":"Edit text files. Do not use this tool to edit Jupyter notebooks. apply_patch allows you to execute a diff/patch against a text file, but the format of the diff specification is unique to this task, so pay careful attention to these instructions. To use the apply_patch command, you should pass a message of the following structure as "input":\n\n*** Begin Patch\n[YOUR_PATCH]\n*** End Patch\n\nWhere [YOUR_PATCH] is the actual content of your patch, specified in the following V4A diff format.\n\n*** [ACTION] File: [/absolute/path/to/file] -> ACTION can be one of Add, Update, or Delete.\nAn example of a message that you might pass as "input" to this function, in order to apply a patch, is shown below.\n\n*** Begin Patch\n*** Update File: /Users/someone/pygorithm/searching/binary_search.py\n@@Class BaseClass\n@@ def search():\n- pass\n+ raise NotImplementedError()\n\n@@Class Subclass\n@@ def search():\n- pass\n+ raise NotImplementedError()\n\n*** End Patch\nDo not use line numbers in this diff format.","parameters":{"type":"object","properties":{"input":{"type":"string","description":"The edit patch to apply."},"explanation":{"type":"string","description":"A short description of what the tool call is aiming to achieve."}},"required":["input","explanation"]}}},{"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":{"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"]}}},{"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":"integer","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 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":"integer","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","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":"open_simple_browser","description":"Preview a website or open a URL in the editor's Simple Browser. Useful for quickly viewing locally hosted websites, demos, or resources without leaving the coding environment.","parameters":{"type":"object","properties":{"url":{"type":"string","description":"The website URL to preview or open in the Simple Browser inside the editor. Must be either an http or https URL"}},"required":["url"]}}},{"type":"function","function":{"name":"read_file","description":"Read the contents of a file. Line numbers are 1-indexed. This tool will truncate its output at 2000 lines and may be called repeatedly with offset and limit parameters to read larger files in chunks.","parameters":{"type":"object","required":["filePath"],"properties":{"filePath":{"description":"The absolute path of the file to read.","type":"string"},"offset":{"description":"Optional: the 1-based line number to start reading from. Only use this if the file is too large to read at once. If not specified, the file will be read from the beginning.","type":"integer"},"limit":{"description":"Optional: the maximum number of lines to read. Only use this together with offset if the file is too large to read at once.","type":"integer"}}}}},{"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 as untitled: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 <command>."},"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_task_output","description":"Get the output of a task","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The task ID for which to get the output."},"workspaceFolder":{"type":"string","description":"The workspace folder path containing the task"}},"required":["id","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":"integer","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":"run_task","description":"Runs a VS Code task.\n\n- If you see that an appropriate task exists for building or running code, prefer to use this tool to run the task instead of using the run_in_terminal tool.\n- Make sure that any appropriate build or watch task is running before trying to run tests or execute code.\n- If the user asks to run a task, use this tool to do so.","parameters":{"type":"object","properties":{"workspaceFolder":{"type":"string","description":"The workspace folder path containing the task"},"id":{"type":"string","description":"The task ID to run."}},"required":["workspaceFolder","id"]}}},{"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_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 and retrieving information related to GitHub pull requests (PRs). The tools allow users to access detailed information about both active and open pull requests, including titles, descriptions, lists of changed files, review comments, and the current state of the PRs. They also provide insights into status checks and continuous integration (CI) results, which are crucial for assessing the quality and readiness of code changes before merging. Additionally, for PRs created by Copilot, session logs are available, offering a glimpse into the development process and decisions made by the coding agent.\n\nThe 'github-pull-request_activePullRequest' tool is specifically designed to fetch details about the currently checked-out pull request, making it the go-to tool for real-time updates and information. In contrast, the 'github-pull-request_openPullRequest' tool retrieves details about any currently visible pull request, regardless of whether it is checked out or not. This distinction allows users to manage their workflow effectively, whether they are actively working on a PR or reviewing others.\n\nThese tools can be used together to provide a comprehensive overview of the pull request landscape within a repository. For instance, a developer can first check the active PR for immediate changes and then look at open PRs to understand the broader context of ongoing work. This synergy enhances collaboration and ensures that all team members are aligned on the current state of code contributions.\n\nOverall, these tools are essential for developers and teams working with GitHub, as they streamline the process of tracking and managing pull requests, ultimately leading to more efficient code reviews and integrations.\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_github_search_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 searching within GitHub repositories using natural language queries. The 'github-pull-request_formSearchQuery' tool converts user-friendly natural language into a well-formed GitHub search query, ensuring that users can easily express what they are looking for without needing to know the specific syntax required by GitHub's search functionality. This tool acts as a prerequisite for the search process, making it accessible for users of all technical levels.\n\nOnce the search query is formulated, the 'github-pull-request_doSearch' tool executes the search on GitHub, returning relevant results based on the query provided. This two-step process allows users to efficiently find pull requests, issues, or other relevant content within GitHub, enhancing their ability to navigate and manage projects.\n\nTogether, these tools empower users to conduct targeted searches that can uncover valuable information, such as finding specific pull requests related to a feature, identifying issues that need attention, or exploring code changes across repositories. This capability is particularly useful for developers and project managers who need to stay informed about ongoing work and contributions.\n\nBy leveraging these tools, teams can improve their workflow and collaboration, as they can quickly locate relevant discussions and code changes, leading to more informed decision-making and faster resolution of issues. Overall, this group of tools enhances the search experience within GitHub, making it easier to access and utilize the wealth of information available in repositories.\n\nBe sure to call this tool if you need a capability related to the above.","parameters":{"type":"object","properties":{}}}},{"type":"function","function":{"name":"github-pull-request_copilot-coding-agent","description":"Completes the provided task using an asynchronous coding agent. Use when the user wants copilot continue completing a task in the background or asynchronously. IMPORTANT: Use this tool LAST/FINAL when users mention '#github-pull-request_copilot-coding-agent' in their query. This indicates they want the task/job implemented by the remote coding agent after all other analysis, planning, and preparation is complete. Call this tool at the END to hand off the fully-scoped task to the asynchronous GitHub Copilot coding agent. The agent will create a new branch, implement the changes, and open a pull request. Always use this tool as the final step when the hashtag is mentioned, after completing any other necessary tools or analysis first.","parameters":{"type":"object","required":["title","body"],"properties":{"title":{"type":"string","description":"The title of the issue. Populate from chat context."},"body":{"type":"string","description":"The body/description of the issue. Populate from chat context."},"existingPullRequest":{"type":"number","description":"The number of an existing pull request related to the current coding agent task. Look in the chat history for this number. In the chat it may look like 'Coding agent will continue work in #17...'. In this example, you should return '17'."}}}}},{"type":"function","function":{"name":"github-pull-request_renderIssues","description":"Render issue items from an issue search in a markdown table. The markdown table will be displayed directly to the user by the tool. No further display should be done after this!","parameters":{"type":"object","properties":{"arrayOfIssues":{"type":"array","description":"An array of GitHub Issues.","items":{"type":"object","properties":{"title":{"type":"string","description":"The title of the issue."},"number":{"type":"number","description":"The number of the issue."},"url":{"type":"string","description":"The URL of the issue."},"state":{"type":"string","description":"The state of the issue (open/closed)."},"createdAt":{"type":"string","description":"The creation date of the issue."},"updatedAt":{"type":"string","description":"The last update date of the issue."},"closedAt":{"type":"string","description":"The closing date of the issue."},"author":{"type":"object","description":"The author of the issue.","properties":{"login":{"type":"string","description":"The login of the author."},"url":{"type":"string","description":"The URL of the author's profile."}}},"labels":{"type":"array","description":"The labels associated with the issue.","items":{"type":"object","properties":{"name":{"type":"string","description":"The name of the label."},"color":{"type":"string","description":"The color of the label."}}}},"assignees":{"type":"array","description":"The assignees of the issue.","items":{"type":"object","properties":{"login":{"type":"string","description":"The login of the assignee."},"url":{"type":"string","description":"The URL of the assignee's profile."}}}},"commentsCount":{"type":"integer","description":"The number of comments on the issue."}},"required":["title","number","url","state","createdAt","author"]}},"totalIssues":{"type":"number","description":"The total number of issues in the search."}},"required":["arrayOfIssues","totalIssues"]}}},{"type":"function","function":{"name":"github-pull-request_suggest-fix","description":"Summarize and suggest a fix for a GitHub issue.","parameters":{"type":"object","properties":{"repo":{"type":"object","description":"The repository to get the issue from.","properties":{"owner":{"type":"string","description":"The owner of the repository to get the issue from."},"name":{"type":"string","description":"The name of the repository to get the issue from."}},"required":["owner","name"]},"issueNumber":{"type":"number","description":"The number of the issue to get."}},"required":["issueNumber","repo"]}}},{"type":"function","function":{"name":"activate_form_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 for interacting with web forms and input elements on a webpage. The tools allow users to perform actions such as clicking on elements, filling out text fields, and selecting options from dropdown menus. The 'mcp_chromedevtool_fill_form' tool enhances efficiency by enabling the filling of multiple form elements simultaneously, which is particularly useful for complex forms. Additionally, the 'mcp_chromedevtool_press_key' tool provides the capability to simulate keyboard actions, allowing for the execution of shortcuts or navigation commands that may not be achievable through standard input methods. The 'mcp_chromedevtool_wait_for' tool adds a layer of synchronization by allowing scripts to pause until specific text appears on the page, ensuring that actions are performed at the right moment. Together, these tools facilitate comprehensive automation of form interactions, making them ideal for testing and data entry 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_page_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 that manage browser pages and their navigation. The tools provide functionalities such as creating new pages, closing existing ones, and navigating to specific URLs. The 'mcp_chromedevtool_list_pages' tool allows users to retrieve a list of all open pages, which is essential for managing multiple tabs effectively. Additionally, the 'mcp_chromedevtool_resize_page' tool enables users to adjust the dimensions of the selected page's window, which can be useful for testing responsive designs. The 'mcp_chromedevtool_emulate' tool allows for the simulation of various features on the selected page, enhancing testing capabilities. By combining these tools, users can efficiently control and manipulate browser pages, making them invaluable for web testing and development 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_element_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 focuses on advanced interactions with elements on a webpage, specifically through dragging and hovering actions. The 'mcp_chromedevtool_drag' tool allows users to simulate dragging one element over another, which is essential for testing drag-and-drop functionalities commonly found in modern web applications. The 'mcp_chromedevtool_hover' tool enables users to simulate mouse hover actions, which can trigger various UI changes such as tooltips, dropdowns, or animations. Together, these tools provide a robust framework for testing interactive elements, ensuring that user interactions behave as expected. They are particularly useful for developers and testers who need to validate the dynamic behavior of web applications.\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_console_logging_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 includes tools that facilitate the management and retrieval of console messages within a web page. The 'mcp_chromedevtool_list_console_messages' tool allows users to view all console messages generated since the last navigation, providing insights into the page's behavior and any potential errors. The 'mcp_chromedevtool_get_console_message' tool enables users to retrieve specific console messages by their ID, allowing for targeted debugging and analysis. These tools are essential for developers who need to monitor and troubleshoot JavaScript execution and other console outputs during the development and testing phases. By utilizing these tools, users can gain a deeper understanding of the application's performance and identify issues that may arise during user interactions.\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_performance_monitoring_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 is dedicated to monitoring and analyzing the performance of web pages. The tools allow users to start and stop performance trace recordings, which capture detailed metrics about page load times and responsiveness. This is crucial for identifying performance bottlenecks and optimizing web applications. The recorded traces also provide insights into Core Web Vitals (CWV) scores, which are essential for assessing user experience. By leveraging these tools, developers can gain a deeper understanding of how their pages perform under various conditions, enabling them to make informed decisions about optimizations and enhancements to improve overall performance.\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_visual_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 of tools is focused on capturing visual representations of web pages. Users can take screenshots of entire pages or specific elements, which is useful for documentation, reporting, or visual testing. Additionally, the tools offer the capability to take text snapshots based on the accessibility (a11y) tree of the page. This feature provides a structured overview of page elements along with unique identifiers, making it easier to analyze the content and structure of a webpage. By using these tools together, users can create comprehensive visual and textual records of web pages, which can be invaluable for accessibility audits, design reviews, and quality assurance processes.\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_chromedevtool_evaluate_script","description":"Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON\nso returned values have to JSON-serializable.","parameters":{"type":"object","properties":{"function":{"type":"string","description":"A JavaScript function declaration to be executed by the tool in the currently selected page.\nExample without arguments: () => {\n return document.title\n}orasync () => {\n return await fetch("example.com")\n}.\nExample with arguments: (el) => {\n return el.innerText;\n}\n"},"args":{"type":"array","items":{"type":"object","properties":{"uid":{"type":"string","description":"The uid of an element on the page from the page content snapshot"}},"required":["uid"],"additionalProperties":false},"description":"An optional list of arguments to pass to the function."}},"required":["function"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_chromedevtool_get_network_request","description":"Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel.","parameters":{"type":"object","properties":{"reqid":{"type":"integer","description":"The reqid of the network request. If omitted returns the currently selected request in the DevTools Network panel."}},"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_chromedevtool_handle_dialog","description":"If a browser dialog was opened, use this command to handle it","parameters":{"type":"object","properties":{"action":{"type":"string","enum":["accept","dismiss"],"description":"Whether to dismiss or accept the dialog"},"promptText":{"type":"string","description":"Optional prompt text to enter into the dialog."}},"required":["action"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_chromedevtool_performance_analyze_insight","description":"Provides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording.","parameters":{"type":"object","properties":{"insightSetId":{"type":"string","description":"The id for the specific insight set. Only use the ids given in the \"Available insight sets\" list."},"insightName":{"type":"string","description":"The name of the Insight you want more information on. For example: \"DocumentLatency\" or \"LCPBreakdown\""}},"required":["insightSetId","insightName"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_chromedevtool_upload_file","description":"Upload a file through a provided element.","parameters":{"type":"object","properties":{"uid":{"type":"string","description":"The uid of the file input element or an element that will open file chooser on the page from the page content snapshot"},"filePath":{"type":"string","description":"The local path of the file to upload"}},"required":["uid","filePath"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_claude-code-m_claude_code","description":"Claude Code Agent: Your versatile multi-modal assistant for code, file, Git, and terminal operations via Claude CLI. Use workFolderfor contextual execution.\n\n• File ops: Create, read, (fuzzy) edit, move, copy, delete, list files, analyze/ocr images, file content analysis\n └─ e.g., \"Create /tmp/log.txt with 'system boot'\", \"Edit main.py to replace 'debug_mode = True' with 'debug_mode = False'\", \"List files in /src\", \"Move a specific section somewhere else\"\n\n• Code: Generate / analyse / refactor / fix\n └─ e.g. \"Generate Python to parse CSV→JSON\", \"Find bugs in my_script.py\"\n\n• Git: Stage ▸ commit ▸ push ▸ tag (any workflow)\n └─ \"Commit '/workspace/src/main.java' with 'feat: user auth' to develop.\"\n\n• Terminal: Run any CLI cmd or open URLs\n └─ \"npm run build\", \"Open https://developer.mozilla.org\"\n\n• Web search + summarise content on-the-fly\n\n• Multi-step workflows (Version bumps, changelog updates, release tagging, etc.)\n\n• GitHub integration Create PRs, check CI status\n\n• Confused or stuck on an issue? Ask Claude Code for a second opinion, it might surprise you!\n\n**Prompt tips**\n\n1. Be concise, explicit & step-by-step for complex tasks. No need for niceties, this is a tool to get things done.\n2. For multi-line text, write it to a temporary file in the project root, use that file, then delete it.\n3. If you get a timeout, split the task into smaller steps.\n4. **Seeking a second opinion/analysis**: If you're stuck or want advice, you can askclaude_code` to analyze a problem and suggest solutions. Clearly state in your prompt that you are looking for analysis only and no actual file modifications should be made.\n5. If workFolder is set to the project path, there is no need to repeat that path in the prompt and you can use relative paths for files.\n6. Claude Code is really good at complex multi-step file operations and refactorings and faster than your native edit features.\n7. Combine file operations, README updates, and Git commands in a sequence.\n8. Claude can do much more, just ask it!\n\n ","parameters":{"type":"object","properties":{"prompt":{"type":"string","description":"The detailed natural language prompt for Claude to execute."},"workFolder":{"type":"string","description":"Mandatory when using file operations or referencing any file. The working directory for the Claude CLI execution. Must be an absolute path."}},"required":["prompt"]}}},{"type":"function","function":{"name":"activate_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 for interacting with web pages through various automated actions. They enable users to perform essential browser operations such as clicking on elements, navigating to URLs, and handling dialog boxes. The tools also allow for keyboard interactions, including typing text and pressing keys, which can be crucial for filling out forms or executing commands on web applications. Additionally, users can resize the browser window and hover over elements, enhancing the ability to manipulate the user interface dynamically.\n\nThese tools can be used together to create automated scripts that simulate user behavior on web pages. For instance, a user could navigate to a specific URL, fill out a form by typing text and selecting options, and then submit the form by clicking a button. The ability to handle dialogs and perform keyboard actions further extends the functionality, making it possible to interact with complex web applications seamlessly.\n\nOverall, this group is essential for developers and testers who need to automate web interactions for testing purposes, data entry, or web scraping. By combining these tools, users can create robust automation workflows that mimic real user interactions, ensuring that web applications function as intended under various scenarios.\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 provided allow users to fill out multiple form fields efficiently, which is particularly useful for applications that require extensive data entry. By automating the process of filling forms, users can save time and reduce the likelihood of errors associated with manual input.\n\nIn addition to form filling, the tools also facilitate file uploads, enabling users to upload one or multiple files seamlessly. This capability is crucial for applications that require users to submit documents, images, or other file types as part of their interaction. The combination of form filling and file uploading allows for comprehensive data submission processes, making it easier for users to complete tasks that involve both textual and file-based inputs.\n\nThese tools are particularly beneficial for developers and testers who need to simulate user interactions with forms and file uploads during testing phases. By automating these processes, they can ensure that the application handles data submissions correctly and efficiently, ultimately improving the user experience.\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_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, focusing on accessibility and standard screenshots. The 'snapshot' tool captures an accessibility snapshot of the current page, providing a more detailed view that is better suited for analyzing the page's structure and accessibility features compared to a standard screenshot. This is particularly useful for developers and accessibility testers who need to evaluate how well a web page meets accessibility standards.\n\nOn the other hand, the 'screenshot' tool allows users to take a traditional screenshot of the current page. While this captures the visual appearance of the page, it does not provide the same level of detail for accessibility analysis as the snapshot tool. Users can utilize these tools in tandem to document both the visual layout and the accessibility aspects of a web page, ensuring comprehensive evaluations.\n\nThese tools are essential for quality assurance teams, web developers, and accessibility advocates who need to assess and report on the usability and accessibility of web applications. By capturing both types of images, they can create thorough documentation that supports improvements and compliance with accessibility guidelines.\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":{"onlyErrors":{"type":"boolean","description":"Only return error messages"}},"additionalProperties":false}}},{"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}}},{"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}}},{"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}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_navigate_back","description":"Go back to the previous page","parameters":{"type":"object","properties":{},"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_network_requests","description":"Returns all network requests since loading the page","parameters":{"type":"object","properties":{},"additionalProperties":false}}},{"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":"integer","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false}}},{"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}}},{"type":"function","function":{"name":"activate_requirements_gathering_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 the collection, analysis, and configuration of project requirements. The 'mcp_spec-kit-proj_gather' tool initiates the process by collecting user input on project needs, generating structured questions to ensure clarity and completeness. It supports multi-turn interactions, allowing for iterative refinement of the requirements. Once the information is gathered, the 'mcp_spec-kit-proj_analyze' tool evaluates the completeness and clarity of the requirements. If the requirements are deemed sufficient, it generates a summary and provides commands for further action. If not, it prompts the user to gather additional information. Finally, the 'mcp_spec-kit-proj_configure' tool provides a user-friendly interface for users to fill in the details of the requirements through a web-based form, ensuring that all necessary information is captured effectively. Together, these tools streamline the requirements gathering process, making it more efficient and user-centric.\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_spec_kit_building_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 the construction and understanding of Spec Kit commands, which are essential for project development. The 'mcp_spec-kit-proj_build' tool takes the finalized requirements and generates seven specific commands that guide the project workflow, ensuring high performance and maintainability through its use of modern technologies like Vue 3 and TypeScript. To aid users in navigating these commands, the 'mcp_spec-kit-proj_learn_speckit' tool provides an interactive web interface that details each command's purpose, usage, and best practices, making it easier for users to familiarize themselves with the Spec Kit framework. After building the commands, the 'mcp_spec-kit-proj_preview' tool allows users to visually inspect the results in a web format, enhancing usability by providing a clear and aesthetically pleasing presentation of the command outputs. Collectively, these tools empower users to effectively build, learn, and preview their Spec Kit commands, facilitating a smoother development process.\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_upstash_conte_get-library-docs","description":"Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.","parameters":{"type":"object","properties":{"context7CompatibleLibraryID":{"type":"string","description":"Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."},"topic":{"type":"string","description":"Topic to focus documentation on (e.g., 'hooks', 'routing')."},"tokens":{"type":"number","description":"Maximum number of tokens of documentation to retrieve (default: 5000). Higher values provide more context but consume more tokens."}},"required":["context7CompatibleLibraryID"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_upstash_conte_resolve-library-id","description":"Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Trust score (consider libraries with scores of 7-10 more authoritative)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.","parameters":{"type":"object","properties":{"libraryName":{"type":"string","description":"Library name to search for and retrieve a Context7-compatible library ID."}},"required":["libraryName"],"additionalProperties":false}}},{"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}}},{"type":"function","function":{"name":"mcp_spec-kit-proj_configure","description":"接收需求配置文件路径，打开可视化界面让用户填写需求详情。该工具会启动本地 Web 服务器，在浏览器中展示配置表单，等待用户填写并提交。","parameters":{"type":"object","properties":{"configFilePath":{"type":"string","description":"需求配置 JSON 文件的路径"}},"required":["configFilePath"],"additionalProperties":false}}},{"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}}},{"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}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_click","description":"Perform click on a web page","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"},"doubleClick":{"type":"boolean","description":"Whether to perform a double click instead of a single click"},"button":{"type":"string","enum":["left","right","middle"],"description":"Button to click, defaults to left"},"modifiers":{"type":"array","items":{"type":"string","enum":["Alt","Control","ControlOrMeta","Meta","Shift"]},"description":"Modifier keys to press"}},"required":["element","ref"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_close","description":"Close the page","parameters":{"type":"object","properties":{},"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_microsoft_pla_browser_hover","description":"Hover over element on page","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"}},"required":["element","ref"],"additionalProperties":false}}},{"type":"function","function":{"name":"mcp_spec-kit-proj_gather","description":"收集用户的项目需求信息，生成结构化的需求问题配置。该工具会返回提示词，AI 根据提示词生成需求配置 JSON，然后调用 configure 工具让用户填写。支持多回合收集。","parameters":{"type":"object","properties":{"projectIdea":{"type":"string","description":"用户的项目想法描述，例如：我想做一个待办事项应用"},"userResponse":{"type":"string","description":"用户之前填写的回答文本（可选），如果是第一次调用则不需要此参数"},"previousFeedback":{"type":"string","description":"用户的修改意见（可选），如果是第一次调用则不需要此参数"},"sessionId":{"type":"string","description":"会话ID（可选），如果提供则继续现有会话，否则创建新会话"}},"required":["projectIdea"],"additionalProperties":false}}}],"tool_choice":"auto"}

========================================
=== RESPONSE ===
Status: 401
Access-Control-Allow-Origin: *
Access-Control-Allow-Methods: GET, POST, PUT, DELETE, OPTIONS
Access-Control-Allow-Headers: *

{"error":"Invalid API key"}

[luispater]

{"error":"Invalid API key"}

This error means you didn't set a valid key for the LLM client (like kilo, cherry, codex, etc.).

Please check the api key is correct.

It MUST be an item from section api-keys in the config.yaml.