Constant Field Values

Contents

com.alibaba.*

  • com.alibaba.cloud.ai.graph.agent.DefaultBuilder
    Modifier and Type
    Constant Field
    Value
    public static final String
    POSSIBLE_LLM_TOOL_NAME_CHANGE_WARNING
    "LLM may have adapted the tool name \'{}\', especially if the name was truncated due to length limits. If this is the case, you can customize the prefixing and processing logic using McpToolNamePrefixGenerator"
  • com.alibaba.cloud.ai.graph.agent.Prioritized
    Modifier and Type
    Constant Field
    Value
    public static final int
    HIGHEST_PRECEDENCE
    -2147483648
    public static final int
    LOWEST_PRECEDENCE
    2147483647
  • com.alibaba.cloud.ai.graph.agent.extension.tools.filesystem.EditFileTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Performs exact string replacements in files.\n\nUsage:\n- You must use your `read_file` tool at least once before editing.\n- When editing text from read_file output, preserve exact indentation\n- ALWAYS prefer editing existing files. NEVER write new files unless explicitly required.\n- The edit will FAIL if `old_string` is not unique in the file.\n- After editing, verify the changes by using the read_file tool.\n"
  • com.alibaba.cloud.ai.graph.agent.extension.tools.filesystem.GlobTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Find files matching a glob pattern.\n\nUsage:\n- Supports standard glob patterns: `*` (any characters), `**` (any directories), `?` (single character)\n- Returns a list of absolute file paths that match the pattern\n\nExamples:\n- `**/*.java` - Find all Java files\n- `*.txt` - Find all text files in root\n- `/src/**/*.xml` - Find all XML files under /src\n"
  • com.alibaba.cloud.ai.graph.agent.extension.tools.filesystem.GrepTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Search for a pattern in files.\n\nUsage:\n- The pattern parameter is the text to search for (literal string, not regex)\n- The path parameter filters which directory to search in\n- The glob parameter accepts a glob pattern to filter which files to search\n\nExamples:\n- Search all files: `grep(pattern=\"TODO\")`\n- The search is case-sensitive by default.\n"
  • com.alibaba.cloud.ai.graph.agent.extension.tools.filesystem.ListFilesTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Lists all files in the filesystem, filtering by directory.\n\nUsage:\n- The path parameter must be an absolute path, not a relative path\n- The list_files tool will return a list of all files in the specified directory.\n- This is very useful for exploring the file system and finding the right file to read or edit.\n- You should almost ALWAYS use this tool before using the Read or Edit tools.\n"
  • com.alibaba.cloud.ai.graph.agent.extension.tools.filesystem.ReadFileTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Reads a file from the filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 500 lines starting from the beginning of the file\n- **IMPORTANT for large files and codebase exploration**: Use pagination with offset and limit parameters to avoid context overflow\n - First scan: read_file(path, limit=100) to see file structure\n - Read more sections: read_file(path, offset=100, limit=200) for next 200 lines\n - Only omit limit (read full file) when necessary for editing\n- Specify offset and limit: read_file(path, offset=0, limit=100) reads first 100 lines\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.\n\t\t\t- You should almost ALWAYS use the list_files tool before using this tool to verify the file path.\n"
  • com.alibaba.cloud.ai.graph.agent.extension.tools.filesystem.WriteFileTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Writes to a new file in the filesystem.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- The content parameter must be a string\n- The write_file tool will create a new file.\n- When writing to a file, the content will completely replace the existing content.\n"
  • com.alibaba.cloud.ai.graph.agent.flow.agent.LoopAgent
    Modifier and Type
    Constant Field
    Value
    public static final String
    LOOP_STRATEGY
    "loopStrategy"
  • com.alibaba.cloud.ai.graph.agent.hook.skills.ReadSkillTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DESCRIPTION
    "Reads the full content of a skill from the SkillRegistry.\nYou can use this tool to read the complete content of any skill by providing its name.\n\nUsage:\n- The skill_name parameter must match the name of the skill as registered in the registry\n- The tool returns the full content of the skill file (e.g., SKILL.md) without frontmatter\n- If the skill is not found, an error will be returned\n\nExample:\n- read_skill(\"pdf-extractor\")\n"
    public static final String
    READ_SKILL
    "read_skill"
  • com.alibaba.cloud.ai.graph.agent.tools.ShellTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DEFAULT_TOOL_DESCRIPTION
    "Execute a shell command inside a persistent session. Before running a command, confirm the working directory is correct (e.g., inspect with `ls` or `pwd`) and ensure any parent directories exist. Prefer absolute paths and quote paths containing spaces, such as `cd \"/path/with spaces\"`. Chain multiple commands with `&&` or `;` instead of embedding newlines. Avoid unnecessary `cd` usage unless explicitly required so the session remains stable. Outputs may be truncated when they become very large, and long running commands will be terminated once their configured timeout elapses."
  • com.alibaba.cloud.ai.graph.agent.tools.ShellTool2
    Modifier and Type
    Constant Field
    Value
    public static final String
    DEFAULT_TOOL_DESCRIPTION
    "Execute a shell command inside a persistent session. Before running a command, confirm the working directory is correct (e.g., inspect with `ls` or `pwd`) and ensure any parent directories exist. Prefer absolute paths and quote paths containing spaces, such as `cd \"/path/with spaces\"`. Chain multiple commands with `&&` or `;` instead of embedding newlines. Avoid unnecessary `cd` usage unless explicitly required so the session remains stable. Outputs may be truncated when they become very large, and long running commands will be terminated once their configured timeout elapses."
  • com.alibaba.cloud.ai.graph.agent.tools.ToolContextConstants
    Modifier and Type
    Constant Field
    Value
    public static final String
    AGENT_CONFIG_CONTEXT_KEY
    "_AGENT_CONFIG_"
    public static final String
    AGENT_STATE_CONTEXT_KEY
    "_AGENT_STATE_"
    public static final String
    AGENT_STATE_FOR_UPDATE_CONTEXT_KEY
    "_AGENT_STATE_FOR_UPDATE_"
  • com.alibaba.cloud.ai.graph.agent.tools.WebFetchTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DEFAULT_TOOL_DESCRIPTION
    "Fetches content from a specified URL and processes it using an AI model.\n\nFeatures:\n- Takes a URL and a prompt as input\n- Fetches the URL content using HTTP GET method\n- Converts HTML to markdown\n- Processes the content with the prompt using a small, fast model\n- Returns the model\'s response about the content\n- Includes a self-cleaning 15-minute cache for faster responses\n- Automatic retry on network errors and 5xx server errors\n\nUsage notes:\n- IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead.\n- The URL must be a fully-formed valid URL (e.g., https://example.com)\n- HTTP URLs will be automatically upgraded to HTTPS\n- Only HTTP GET requests are supported (read-only)\n- The prompt should describe what information you want to extract from the page\n- This tool is read-only and does not modify any files or send any data\n- Results may be summarized if the content is very large\n- Retries up to 2 times (configurable) on transient failures with exponential backoff\n"
  • com.alibaba.cloud.ai.graph.agent.tools.WriteTodosTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DEFAULT_TOOL_DESCRIPTION
    "Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\nUse this tool proactively in these scenarios:\n\n1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos\n6. When you start working on a task - Mark it as in_progress BEFORE beginning work. Ideally you should only have one todo as in_progress at a time\n7. After completing a task - Mark it as completed and add any new follow-up tasks discovered during implementation\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. The task is purely conversational or informational\n\nNOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.\n\n## Validation Rules\n\nThe tool validates the following:\n- Task content must not be empty or blank\n- All tasks must have valid status values (pending, in_progress, completed)\n\n## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you\'re done!\nAssistant: I\'ll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Creating dark mode toggle component in Settings page\n2. Adding dark mode state management (context/store)\n3. Implementing CSS-in-JS styles for dark theme\n4. Updating existing components to support theme switching\n5. Running tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of \'getCwd\'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I\'ve found 15 instances of \'getCwd\' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I\'ll help implement these features. First, let\'s add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let\'s start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print \'Hello World\' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\nprint(\"Hello World\")\nThis will output the text \"Hello World\" to the console when executed.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There\'s no need to track multiple tasks or steps for such a straightforward request.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven\'t, and which files aren\'t being tracked by Git.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn\'t require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n- pending: Task not yet started\n- in_progress: Currently working on (limit to ONE task at a time for sequential work)\n- completed: Task finished successfully\n\n**IMPORTANT**: Task descriptions must have two forms:\n- content: The imperative form describing what needs to be done (e.g., \"Run tests\", \"Build the project\")\n- activeForm: The present continuous form shown during execution (e.g., \"Running tests\", \"Building the project\")\n\n2. **Task Management**:\n- Update task status in real-time as you work\n- Mark tasks complete IMMEDIATELY after finishing (don\'t batch completions)\n- Exactly ONE task should be in_progress at any time for sequential workflows\n- Complete current tasks before starting new ones\n- Remove tasks that are no longer relevant from the list entirely\n\n3. **Task Completion Requirements**:\n- ONLY mark a task as completed when you have FULLY accomplished it\n- If you encounter errors, blockers, or cannot finish, keep the task as in_progress\n- When blocked, create a new task describing what needs to be resolved\n- Never mark a task as completed if:\n\t- Tests are failing\n\t- Implementation is partial\n\t- You encountered unresolved errors\n\t- You couldn\'t find necessary files or dependencies\n\n4. **Task Breakdown**:\n- Create specific, actionable items\n- Break complex tasks into smaller, manageable steps\n- Use clear, descriptive task names\n- Always provide both forms:\n\t- content: \"Fix authentication bug\"\n\t- activeForm: \"Fixing authentication bug\"\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n"
    public static final String
    SUCCESS_MESSAGE
    "Todos have been modified successfully. Ensure that you continue to use the todo list to track your progress. Please proceed with the current tasks if applicable."
  • com.alibaba.cloud.ai.graph.agent.tools.task.TaskOutputTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DEFAULT_DESCRIPTION
    "Retrieves output from a running or completed background task (sub-agent).\n\nUse when:\n- A Task was launched with run_in_background=true\n- You need to check status or get results from a background sub-agent\n\nParameters:\n- task_id: The task ID returned by the Task tool when run_in_background was true\n- block: Whether to wait for completion (default: true)\n- timeout: Max wait time in milliseconds (default: 30000, max: 600000)\n"
  • com.alibaba.cloud.ai.graph.agent.tools.task.TaskTool
    Modifier and Type
    Constant Field
    Value
    public static final String
    DEFAULT_DESCRIPTION
    "Launch a specialized sub-agent to handle complex, multi-step tasks autonomously.\n\nUse this tool when:\n- The task requires exploring codebases, researching, or multi-step execution\n- You need to delegate to an agent with specific expertise (e.g., Explore, general-purpose)\n- The task would consume too much context if done directly\n\nAvailable sub-agent types and their capabilities:\n%s\n\nParameters:\n- description: Short (3-5 word) summary of what the agent will do\n- prompt: The detailed task for the sub-agent to perform\n- subagent_type: The type of specialized agent to use (required)\n- run_in_background: Set to true to run asynchronously; use TaskOutput tool to retrieve results later\n\nWhen run_in_background=true, returns a task_id. Use the TaskOutput tool with that task_id to get results.\n"