Skip to main content

​
Task

Defined in the task module.
AI Agent A unit of work that can be executed by an Agent or a custom handler function. Task is the unified abstraction for both AgentManager tasks and Workflow steps. It supports all features from the legacy Task class. Simple Usage: task = Task(description=“Research AI trends”) With action alias (from Task): task = Task(action=“Write a blog post about {{topic}}”) With custom handler function: task = Task( name=“process_data”, action=“Process the input”, handler=my_custom_function ) With loop iteration: task = Task( action=“Process {{item}}”, loop_over=“items”, loop_var=“item” )

​
Constructor

​
description
Optional
No description available.
​
expected_output
Optional
No description available.
​
agent
Optional
No description available.
​
name
Optional
No description available.
​
tools
Optional
No description available.
​
context
Optional
No description available.
​
depends_on
Optional
No description available.
​
async_execution
Optional
default:"False"
No description available.
​
config
Optional
No description available.
​
output_file
Optional
No description available.
​
output_json
Optional
No description available.
​
output_pydantic
Optional
No description available.
​
callback
Optional
No description available.
​
on_task_complete
Optional
No description available.
​
status
str
default:"'not started'"
No description available.
​
result
Optional
No description available.
​
create_directory
Optional
default:"False"
No description available.
​
id
Optional
No description available.
​
images
Optional
No description available.
​
next_tasks
Optional
No description available.
​
task_type
str
default:"'task'"
No description available.
​
condition
Optional
No description available.
​
is_start
bool
default:"False"
No description available.
​
loop_state
Optional
No description available.
​
memory
Any
No description available.
​
quality_check
Any
default:"True"
No description available.
​
input_file
Optional
No description available.
​
rerun
bool
default:"False"
No description available.
​
retain_full_context
bool
default:"False"
No description available.
​
guardrail
Optional
No description available.
​
guardrails
Optional
No description available.
​
max_retries
int
default:"3"
No description available.
​
retry_count
int
default:"0"
No description available.
​
agent_config
Optional
No description available.
​
variables
Optional
No description available.
​
skip_on_failure
bool
default:"False"
No description available.
​
retry_delay
float
default:"0.0"
No description available.
​
on_error
str
default:"'stop'"
No description available.
​
action
Optional
No description available.
​
handler
Optional
No description available.
​
should_run
Optional
No description available.
​
loop_over
Optional
No description available.
​
loop_var
str
default:"'item'"
No description available.
​
execution
Optional
No description available.
​
routing
Optional
No description available.
​
output_config
Optional
No description available.
​
output
Optional
No description available.
​
when
Optional
No description available.
​
then_task
Optional
No description available.
​
else_task
Optional
No description available.
​
autonomy
Optional
No description available.
​
knowledge
Optional
No description available.
​
web
Optional
No description available.
​
reflection
Optional
No description available.
​
planning
Optional
No description available.
​
hooks
Optional
No description available.
​
caching
Optional
No description available.
​
output_variable
Optional
No description available.

​
Methods

depends_on()

Alias for context - returns the list of dependent tasks.

depends_on()

Alias for context - sets the list of dependent tasks.

initialize_memory()

Initialize memory if config exists but memory doesn’t

store_in_memory()

Store content in memory with metadata

execute_callback()

Execute callback and store quality metrics if enabled

execute_callback_sync()

Synchronous wrapper to ensure that execute_callback is awaited,

evaluate_when()

Evaluate the ‘when’ condition against the given context.

get_next_task()

Get the next task name based on the ‘when’ condition evaluation.
  • to_dict: Serialize the Task to a dictionary.

​
Source

View on GitHub

praisonaiagents/task/task.py at line 15

Tasks Concept

Task Configuration

Task Validation