Call an external AI model to handle a subtask.

Supports OpenAI and Anthropic APIs with custom endpoint configuration. Returns response with token usage statistics.

Execute multiple AI subtasks in parallel with result aggregation.

Coordinates concurrent calls to different AI models and aggregates results. Useful for breaking complex problems into independent subtasks.

Execute conditional branching based on AI decision.

First calls AI to evaluate a condition, then executes either true_task or false_task based on the decision. Useful for dynamic workflow control.

设置 Subagent 提供商的 API 配置（持久化保存）

此工具将 API 密钥和基础 URL 保存到配置文件中，下次启动时自动加载。 配置文件位置：~/.subagent_config.json

获取指定提供商的 API 配置信息

列出所有已配置的 AI 提供商

返回所有配置的提供商及其状态，包括密钥预览和配置来源。

Returns: JSON 格式的提供商列表

Example: providers = subagent_config_list()

Get comprehensive system information.

Returns: JSON string containing system details

Get CPU information and current usage.

Returns: JSON string containing CPU details and usage

Get memory (RAM) usage statistics.

Returns: JSON string containing memory usage details

Get disk space information for a path.

Get an environment variable value.

List all environment variables.

Get current date and time.

Get information about the current process.

Returns: JSON string with process details

Open a new browser session and navigate to a URL.

Creates a new browser instance (Chrome or Edge) and navigates to the specified URL. Returns a unique session ID for subsequent operations.

Close a browser session.

Closes the browser window and cleans up all associated resources.

List all active browser sessions.

Returns information about all currently active browser sessions including their URLs, titles, and configuration.

Returns: JSON string with list of active sessions

Navigate to a URL in an existing browser session.

Navigate back in browser history.

Navigate forward in browser history.

Refresh the current page.

Get the HTML source code of the current page.

Get the text content of an element.

Get the current page URL and title.

Click an element on the page.

Waits for the element to be clickable before clicking.

Type text into an input element.

Select an option from a dropdown/select element.

Wait for an element to satisfy a condition.

Take a screenshot of the page or a specific element.

Execute JavaScript code in the page context.

Get browser console logs.

Captures console.log, console.error, console.warn, etc. from the page.

Get browser cookies.

Set a browser cookie.

Delete browser cookies.

Enable network request logging.

After enabling, network requests will be captured and can be retrieved using browser_get_network_logs.

Get captured network request logs.

Requires browser_enable_network_log to be called first.

Fill multiple form fields at once.

Open a new browser tab.

Switch to a different browser tab by index.

Close a browser tab.

List all open tabs in the browser session.

Find multiple elements matching a selector.

Get an attribute value from an element.

Scroll the page or scroll an element into view.

获取浏览器配置设置

设置浏览器配置（保存到配置文件）

重置浏览器配置为默认值

Returns: JSON格式的操作结果

Generate a UUID.

Generate hash of text using specified algorithm.

Convert Unix timestamp to readable date.

Convert date string to Unix timestamp.

Calculate difference between two dates.

Format a date string using custom format.

Safely evaluate a mathematical expression.

Generate a random string.

Generate a strong password.

Check password strength and provide recommendations.

Parse and validate a JSON string.

Format JSON with pretty printing.

Extract value from JSON using dot notation path.

Convert CSV data to JSON.

Convert JSON array to CSV format.

Parse CSV data and return as JSON.

Validate JSON syntax and structure.

Flatten nested JSON object into single-level object.

Merge two JSON objects.

Convert XML to JSON format.

Parse YAML string to JSON.

Convert YAML to formatted JSON.

Convert JSON to YAML format.

Parse TOML configuration file to JSON.

Convert TOML to formatted JSON.

Read the contents of a file.

Write content to a file.

Append content to a file.

List contents of a directory.

Check if a file or directory exists.

Get detailed information about a file or directory.

Search for files in a directory.

Create a directory.

Delete a file (requires confirmation).

Copy a file from source to destination.

Compare two files and show differences.

Compare two text strings and show differences.

Search the web using multiple search engines with智能 fallback.

Features:

• Automatic fallback between search engines (DuckDuckGo -> Bing)

• Intelligent caching to reduce API calls

• Rate limiting protection

• Result deduplication

Advanced web search with multi-engine support and parallel searching.

Features:

• Support for multiple search engines: DuckDuckGo, Bing, Google, Baidu

• Parallel searching across multiple engines

• Intelligent result merging and deduplication

• Smart caching mechanism

• Rate limiting protection

Search for news articles using multiple search engines with fallback.

Features:

• Automatic fallback between news search engines

• Intelligent caching

• Rate limiting protection

• Result deduplication

Clear the search cache.

This will remove all cached search results, forcing fresh searches.

Returns: JSON string with operation result

Get search cache and rate limiter statistics.

Returns: JSON string with cache stats, hit rate, and rate limiter info

Fetch the HTML content of a webpage.

Fetch and extract clean text content from a webpage.

Parse HTML and extract elements using CSS selector.

Download a file from URL and save to disk.

Extract the title from a webpage.

Extract all links from a webpage.

Check the HTTP status of a URL.

Get HTTP headers from a URL.

Validate if a string is a properly formatted URL.

Parse a URL and extract its components.

Make HTTP request with custom headers and body.