Great question. In Prefect 3.x, you can read the actual task run name from the running task using the run context or the runtime helpers. Two easy options: 1) Use the run context (recommended) - Works anywhere inside a running task - Gives you access to the full task_run object (id, name, etc.)

from prefect import task, get_run_logger
from prefect.context import get_run_context

@task(task_run_name="process-{i}")
def my_task(i: int):
    ctx = get_run_context()              # This is a TaskRunContext in a task
    logger = get_run_logger()
    <http://logger.info|logger.info>(f"My task run name is: {ctx.task_run.name}")
    return ctx.task_run.name

2) Use the runtime accessor - A concise, convenience accessor for the current task run

from prefect import task
from prefect.runtime import task_run

@task
def my_task():
    current_name = task_run.name
    # or, in some environments, task_run.name.get()
    return current_name

How task_run_name is set - You can pass a template string that uses your task’s parameter names:

@task(task_run_name="load-{table}-{partition}")
def load(table: str, partition: str): ...

- Or pass a callable that receives the parameters dict:

@task(task_run_name=lambda params: f"load-{params['table']}-{params['partition']}")
def load(table: str, partition: str): ...

Helpful docs: - Run context: get_run_context - Runtime accessors (task run): prefect.runtime.task_run - Task options and run names: Task run names If you share a small snippet of your task, I can show exactly where to grab and use the run name.