Control task execution with stop, pause, resume, or stop task and session actions.
Request model for updating task state
The action to perform on the task
stop, stop_task_and_session Successful Response
View model for representing a task with its execution details
Unique identifier for the task
The LLM model used for this task represented as a string
The task prompt/instruction given to the agent
Current status of the task execution
created, started, finished, stopped Naive UTC timestamp when the task was created
Naive UTC timestamp when the task was started (None if task has not started yet)
Naive UTC timestamp when the task completed (None if still running)
Optional additional metadata associated with the task set by the user
Final output/result of the task
Version of browser-use used for this task (older tasks may not have this set)
Whether the task was successful based on the agent's self-reported output (less reliable than the judge)
Stringified JSON object containing the full report from the judge
Judge verdict - True if the judge found the task to be successful, False otherwise (None if judge is not enabled)
Total cost of the task in USD. This is the sum of all step costs incurred during task execution.
List of actionable suggestions for improving task configuration based on detected issues during execution.