@Marvin I'm working with a Prefect Cloud Automation, and I have a deployment flow triggered when a specific flow run enters the 'Completed' state. In this scenario, I need guidance on the most effective method to retrieve information about the original flow run that initiated the entire process. How can I efficiently access the initial flow run's info/metadata from within the triggered deployment flow run?

You can retrieve information about the original flow run that initiated the process within the triggered deployment flow run using Prefect Cloud's features. Here are some methods you can consider: 1. Use the Prefect Client to retrieve the most recent flow runs. You can filter these runs based on specific criteria, such as the completion status or the associated deployment. Here is an example code snippet:

import asyncio
from prefect import Client

async def get_most_recent_flow_runs():
    client = Client()
    last_3_flow_runs = await client.get_flow_runs(order_by={"end_time": "desc"}, limit=3)
    return last_3_flow_runs

last_3_flow_runs = asyncio.run(get_most_recent_flow_runs())
print(last_3_flow_runs)
assert all(run.state.is_completed() for run in last_3_flow_runs)
assert (end_times := [run.end_time for run in last_3_flow_runs]) == sorted(end_times, reverse=True)

You can find more details in the Prefect Client guide. 2. Prefect Cloud retains flow runs according to the Flow Run Retention Policy setting in your personal account or organization profile. This policy represents the number of days each flow run is available in the Prefect Cloud UI, and via the Prefect CLI and API. You can use these interfaces to access the metadata of the flow runs. More details can be found in the Prefect Cloud rate limits guide. 3. Deployments in Prefect Cloud can take a trigger specification, which configures an automation to run the deployment based on the presence or absence of events. The event data can be passed into the deployment run as parameters via Jinja templating. This could be a way to pass the original flow run's info/metadata to the triggered deployment flow run. More details can be found in the Prefect Cloud deployments guide. Please note that these methods require you to be using Prefect Cloud, as some features may not be available in Prefect Core.