Tasks

​

Classes

​

Task

A task represents a unit of work to be performed by an agent.

​

Parameters

​

Static Methods

_is_file_path

Check if an item is a valid file path. Parameters:

• item (Any): Any object to check

Returns:

• bool: True if the item is a string representing an existing file path

_is_folder_path

Check if an item is a valid folder/directory path. Parameters:

• item (Any): Any object to check

Returns:

• bool: True if the item is a string representing an existing directory

_get_files_from_folder

Recursively get all file paths from a folder. Parameters:

• folder_path (str): Path to the folder

Returns:

• List[str]: List of all file paths in the folder and subfolders

_extract_files_from_context

Extract file paths from context and return cleaned context and file list. Also handles folders by extracting all files from them recursively. Parameters:

• context (Any): The context parameter (can be a list, dict, or any other type)

Returns:

• tuple[Any, List[str]]: (cleaned_context, extracted_files)
  • cleaned_context: Context with file/folder paths removed
  • extracted_files: List of file paths found (including files from folders)

​

Functions

duration

Get the task duration. Returns:

• Optional[float]: Task duration in seconds

validate_tools

Validates each tool in the tools list. If a tool is a class and has a __control__ method, runs that method to verify it returns True. Raises an exception if the __control__ method returns False or raises an exception.

context_formatted

Provides read-only access to the formatted context string. Returns:

• Optional[str]: The formatted context string

context_formatted.setter

Sets the internal _context_formatted attribute. Parameters:

• value (Optional[str]): The formatted context string to be assigned

tools_awaiting_external_execution

Get the list of tool calls awaiting external execution. Returns:

• List[ExternalToolCall]: List of tools awaiting external execution

additional_description

Get additional description from RAG context. Parameters:

• client: The client for RAG operations

Returns:

• str: Additional description from RAG data

attachments_base64

Convert all attachment files to base64 encoded strings. Returns:

• List[str] | None: List of base64 encoded strings, or None if no attachments

price_id

Get or generate the price ID. Returns:

• str: The price ID

task_id

Get or generate the task ID. Returns:

• str: The task ID

get_task_id

Get a formatted task ID. Returns:

• str: Formatted task ID

response

Get the task response. Returns:

• Any: The task response

get_total_cost

Get the total cost for this task. Returns:

• Optional[float]: The total cost

total_cost

Get the total estimated cost of this task. Returns:

• Optional[float]: The estimated cost in USD, or None if not available

total_input_token

Get the total number of input tokens used by this task. Returns:

• Optional[int]: The number of input tokens, or None if not available

total_output_token

Get the total number of output tokens used by this task. Returns:

• Optional[int]: The number of output tokens, or None if not available

tool_calls

Get all tool calls made during this task’s execution. Returns:

• List[Dict[str, Any]]: A list of dictionaries containing information about tool calls

add_tool_call

Add a tool call to the task’s history. Parameters:

• tool_call (Dict[str, Any]): Dictionary containing information about the tool call

canvas_agent_description

Get the canvas agent description. Returns:

• str: Canvas agent description

add_canvas

Add canvas to the task. Parameters:

• canvas: The canvas to add

task_start

Start the task. Parameters:

• agent: The agent assigned to this task

task_end

End the task.

task_response

Set the task response. Parameters:

• model_response: The model response

build_agent_input

Builds the input for the agent, using and then clearing the formatted context. Returns:

• Union[str, List[Union[str, BinaryContent]]]: The agent input (string or list with text and binary content)

set_cache_manager

Set the cache manager for this task. Parameters:

• cache_manager (Any): The cache manager

get_cached_response

Get cached response for the given input text. Parameters:

• input_text (str): The input text to search for in cache
• llm_provider (Optional[Any]): LLM provider for semantic comparison

Returns:

• Optional[Any]: Cached response if found, None otherwise

store_cache_entry

Store a new cache entry. Parameters:

• input_text (str): The input text
• output (Any): The corresponding output

get_cache_stats

Get cache statistics. Returns:

• Dict[str, Any]: Cache statistics

clear_cache

Clear all cache entries.