feat: add scripts for desk lifter control and calibration

[Daniel0813]

No description provided.

[Copilot]

Pull Request Overview

This PR adds Python scripts for controlling a desk lifter via Raspberry Pi GPIO pins, including test scripts, calibration utilities, and height positioning functionality.

Key Changes:

• Added GPIO control scripts for desk up/down movement
• Implemented calibration-based height positioning logic
• Documented calibration measurements and movement rates

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 7 comments.

File	Description
scripts/test_down.py	Test script for verifying DOWN button control via GPIO pin 27
scripts/reset_to_lowest.py	Utility to reset desk to lowest position using 56-second calibrated duration
scripts/move_to_height.py	Main positioning script that resets to lowest then moves to target height based on calibration
scripts/lifter_calibration.txt	Documents measured calibration data (height range and movement rates)

[Copilot]

Inconsistent calibration data documentation: Line 7 states "Up movement rate: 0.55 inches/second" but move_to_height.py uses UP_RATE = 0.54. Additionally, line 6 states "Down movement rate: 0.55 inches/second" but this constant is not defined in move_to_height.py where it's used (line 34 hardcodes 56.0 seconds). Ensure calibration values are consistent across all files.

Suggested change

	Up movement rate: 0.55 inches/second (measured from 23.7" to 29.1" in 10s)
	Up movement rate: 0.54 inches/second (measured from 23.7" to 29.1" in 10s)

[Copilot]

Script violates custom guideline against if __name__ == "__main__" patterns. According to the project's coding guidelines, this should be avoided unless explicitly requested. The code should be left as a top-level script instead.

[Copilot]

Inconsistent calibration data: The calibration file shows Up movement rate: 0.55 inches/second but this script uses UP_RATE = 0.54. This mismatch will cause incorrect positioning calculations.

Suggested change

	UP_RATE = 0.54 # inches per second (from calibration)
	UP_RATE = 0.55 # inches per second (from calibration)

[Copilot]

The error message incorrectly displays the target height using double-quote notation ({target_height}'') instead of inch notation ({target_height}"). The double single-quote is confusing and non-standard.

Suggested change

	raise ValueError(f"Target height {target_height}'' is out of range.")
	raise ValueError(f'Target height {target_height}" is out of range.')

[Copilot]

Inconsistent inch notation throughout the function: Lines 28, 30, 40, 46, and 50 use different notations for inches (double single-quotes '', no notation, or inconsistent formatting). Standardize to use the proper inch symbol (") throughout for clarity and consistency.

[Copilot]

Misleading prompt message: The message says "about 56 seconds from max height" but this function is called during reset which should start from the current position (unknown), not necessarily from max height. This could confuse users if the desk isn't at max height.

Suggested change

	input("Press Enter to move all the way DOWN (about 56 seconds from max height)...")
	input("Press Enter to move all the way DOWN (this will take up to 56 seconds)...")

[Copilot]

Hardcoded magic number: The 56.0 second duration is duplicated from reset_to_lowest.py without explanation. Consider extracting this as a named constant (e.g., MAX_TO_MIN_TIME = 56.0) with a comment explaining its derivation, or better yet, calculate it from (HIGHEST_HEIGHT - LOWEST_HEIGHT) / DOWN_RATE where DOWN_RATE = 0.55.

[sgbaird]

@copilot

See requirements below:

1. someone sets up all the hardware and RPi software per the instructions at https://progressive-automations-python.readthedocs.io/en/latest/
2. they run pip install progressive-automations-python
3. they run prefect cloud login -k <api-key> and whatever other commands are needed to get the workpools/deployments/etc. started (i.e., probably prefect worker start ...)
4. they should also be able to run progressive_automations_python --test <UP or DOWN> or similar for some simple testing
5. they should be able to call run_deployment(...) externally and have the raspberry pi pick that up and execute the command
6. the move command triggered externally via run_deployment should be asynchronous, but there should also be a way to poll the position (i.e., see if it's in its final state), keeping in mind the duty cycle limits and the potential error codes that might occur. Other equipment will have this @flow as a dependency, where it needs to reach the desired position before the next piece of equipment can do its job

Related to last point, including a snippet from context7 chat below:

In Prefect v3, normally I'd run ```from prefect.deployments import run_deployment  run_deployment(     name="custom-movements-flow/custom-movements",     parameters={"position_inches": 35.5} )```, but this is blocking. I want to be able to send a command asynchronously and poll its status for later (similar to baking an oven, preheat to 350 degrees, not sitting in front of the oven the entire time)

I'll help you find the async solution for Prefect v3. Let me fetch the documentation on deployments and async execution.


resolve-library-id
libraryName:
Prefect
Now let me fetch the Prefect documentation focused on async execution and non-blocking deployment runs:


get-library-docs
context7CompatibleLibraryID:
/prefecthq/prefect
topic:
async deployment run_deployment non-blocking
Perfect! I found exactly what you need. Here's how to run a deployment asynchronously and poll its status later in Prefect v3:

Async Non-Blocking Deployment Trigger
Instead of blocking with run_deployment(), you can use await run_deployment() in an async context:

import asyncio
from prefect.deployments import run_deployment

async def trigger_deployment():
    flow_run = await run_deployment(
        name="custom-movements-flow/custom-movements",
        parameters={"position_inches": 35.5}
    )
    return flow_run

# Trigger it without waiting
flow_run = asyncio.run(trigger_deployment())
print(f"Flow run ID: {flow_run.id}")
Return Immediately Without Waiting
If you want to trigger and return immediately (set the oven to 350° and walk away), use timeout=0:

from prefect.deployments import run_deployment

flow_run = run_deployment(
    name="custom-movements-flow/custom-movements",
    parameters={"position_inches": 35.5},
    timeout=0  # Returns immediately
)
print(f"Flow run ID: {flow_run.id}")
Polling the Status Later
Once you have the flow_run object, you can poll its status later:

from prefect.deployments import run_deployment
from prefect import get_client
import asyncio

# Trigger without waiting
flow_run = run_deployment(
    name="custom-movements-flow/custom-movements",
    parameters={"position_inches": 35.5},
    timeout=0
)

# Later... poll the status
async def check_status(flow_run_id):
    async with get_client() as client:
        flow_run = await client.read_flow_run(flow_run_id)
        print(f"Status: {flow_run.state.type}")
        print(f"Result: {flow_run.state.result if flow_run.state_type == 'COMPLETED' else 'Still running'}")
        return flow_run

# Check status anytime
flow_run_status = asyncio.run(check_status(flow_run.id))
Key Parameters:

timeout=0: Returns immediately without waiting for completion
timeout=300: Waits up to 5 minutes for completion
await run_deployment(): Non-blocking async version
This gives you exactly what you need—send the command (preheat to 350°), get back the flow run ID immediately, then check on it whenever you want!

[Copilot]

@sgbaird I've opened a new pull request, #4, to work on those changes. Once the pull request is ready, I'll request review from you.