< Marvin> what is wrong here Engine execution exited with un Prefect Community #marvin-ai

<@ULVA73B9P> what is wrong here? Engine executio...

Mat Partridge

11/01/2025, 8:51 AM

@Marvin what is wrong here? Engine execution exited with unexpected exception Traceback (most recent call last): File "/usr/local/lib/python3.12/site-packages/prefect/flow_engine.py", line 1551, in run_flow parameters=_flow_parameters( ^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/prefect/flow_engine.py", line 1591, in _flow_parameters call_args, call_kwargs = parameters_to_args_kwargs(flow.fn, parameters) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/site-packages/prefect/utilities/callables.py", line 192, in parameters_to_args_kwargs raise SignatureMismatchError.from_bad_params( prefect.exceptions.SignatureMismatchError: Function expects parameters [] but was provided with parameters ['environment'] deployments: - name: my-flow entrypoint: flow.py:dynamic_reporting_pipeline schedules: [] paused: true parameters: environment: "{{ $PREFECT_DEPLOY_ENV }}" from prefect import flow from datetime import datetime from prefect.logging import get_run_logger from prefect import runtime @flow def dynamic_reporting_pipeline(): logger = get_run_logger() env = runtime.flow_run.parameters.get("environment", "unknown") logger.info(f"Running dynamic reporting pipeline in {env} environment")

Marvin

11/01/2025, 8:51 AM

✅ thought for 132.6 seconds

Marvin

11/01/2025, 8:53 AM

You’re getting that SignatureMismatchError because your deployment is supplying a parameter

environment

, but your flow function doesn’t accept any parameters. In Prefect 3.x, any parameters defined in the deployment must match the flow function signature. You have two clean options: Option A — Make

environment

a flow parameter - Keep the deployment

parameters

section - Update the flow to accept

environment

and use it prefect.yaml

Copy code

deployments:
  - name: my-flow
    entrypoint: flow.py:dynamic_reporting_pipeline
    schedules: []
    paused: true
    parameters:
      environment: "{{ $PREFECT_DEPLOY_ENV }}"

flow.py

Copy code

from prefect import flow
from prefect.logging import get_run_logger

@flow
def dynamic_reporting_pipeline(environment: str = "unknown"):
    logger = get_run_logger()
    <http://logger.info|logger.info>(f"Running dynamic reporting pipeline in {environment} environment")

Notes: - Your current

runtime.flow_run.parameters.get(...)

will only work once the parameter exists on the flow (or you can just use the function arg directly as shown). - Make sure your actual code calls

<http://logger.info|logger.info>(...)

— the pasted

<http://logger.info|logger.info>(...)

looks like Slack link formatting, not valid Python. Option B — Use an environment variable instead of a flow parameter - Remove

parameters

from the deployment - Set an environment variable via

job_variables.env

- Read it with

os.getenv

inside your flow prefect.yaml

Copy code

deployments:
  - name: my-flow
    entrypoint: flow.py:dynamic_reporting_pipeline
    schedules: []
    paused: true
    job_variables:
      env:
        PREFECT_DEPLOY_ENV: "{{ $PREFECT_DEPLOY_ENV }}"

flow.py

Copy code

import os
from prefect import flow
from prefect.logging import get_run_logger

@flow
def dynamic_reporting_pipeline():
    logger = get_run_logger()
    env = os.getenv("PREFECT_DEPLOY_ENV", "unknown")
    <http://logger.info|logger.info>(f"Running dynamic reporting pipeline in {env} environment")

Your templating

{{ $PREFECT_DEPLOY_ENV }}

is correct for pulling from the local environment at deploy time. Docs for reference: - prefect.yaml reference: prefect.yaml reference - Customize job variables (env): Customize job variables (env) - Passing flow inputs (parameters): Pass flow inputs (parameters) - Runtime context: prefect.runtime.deployment and prefect.runtime.flow_run

Open in Slack

Previous Next