fix: fix litra-brightness command and setBrightnessPercentage function so 0% and 1% are distinct

[Copilot]

Plan to fix brightness percentage off-by-one bug

• Update percentageWithinRange function in src/utils.ts to use standard percentage formula (0-100)
• Remove the special case for 0% in setBrightnessPercentage function in src/driver.ts
• Update tests in tests/utils.test.ts to reflect new expected behavior
• Update tests in tests/driver.test.ts for setBrightnessPercentage to reflect new expected values
• Run all tests to verify the fix works correctly
• Build the project to ensure no compilation errors
• Request code review and run security checks
• Address code review feedback: Remove redundant Math.round

Summary

Successfully fixed the off-by-one bug where 0% and 1% brightness produced the same value (minimum brightness).

Changes:

1. Updated percentageWithinRange formula: ((percentage - 1) / (100 - 1)) → (percentage / 100)
2. Removed special case for 0% in setBrightnessPercentage
3. Removed redundant Math.round (Math.ceil already returns integers)
4. Updated tests and added verification test for 0% vs 1%

Verification:

• ✅ All 76 tests pass
• ✅ Build successful
• ✅ Linter passed
• ✅ Code review: Feedback addressed
• ✅ Security scan: No vulnerabilities

Behavior (Litra Glow 20-250 lumen):

• 0% → 20 lumen (exact minimum) ✓
• 1% → 23 lumen (above minimum) ✓
• 50% → 135 lumen (midpoint) ✓
• 100% → 250 lumen (exact maximum) ✓

Fixes #556

Original prompt

Problem

As reported in issue #556, there's an off-by-one bug in the brightness percentage calculation where both 0% and 1% brightness return the same value (the minimum brightness).

Current Behavior

In src/driver.ts, the setBrightnessPercentage function has a special case for 0% that returns minimumBrightness, but the percentageWithinRange utility function in src/utils.ts also maps 1% to the minimum brightness due to its formula:

// In utils.ts
export const percentageWithinRange = (
  percentage: number,
  startRange: number,
  endRange: number,
): number => {
  return Math.round(
    Math.ceil(((percentage - 1) / (100 - 1)) * (endRange - startRange) + startRange),
  );
};

For a Litra Glow (min: 20 lumen, max: 250 lumen):

• 0% → 20 lumen (special case)
• 1% → ((1-1)/(100-1)) * (250-20) + 20 = 20 lumen
• 100% → 250 lumen

Both 0% and 1% produce identical results (20 lumen), which is incorrect.

Expected Behavior

Each percentage value from 0-100 should map to a unique brightness value within the device's supported range:

• 0% → minimum brightness (20 lumen for Litra Glow)
• 1% → slightly above minimum
• 100% → maximum brightness (250 lumen for Litra Glow)

Suggested Fix

1. Update the percentageWithinRange function in src/utils.ts to use the standard percentage formula that maps 0-100 to the full range:

export const percentageWithinRange = (
  percentage: number,
  startRange: number,
  endRange: number,
): number => {
  return Math.round(
    Math.ceil((percentage / 100) * (endRange - startRange) + startRange),
  );
};

2. Remove the special case for 0% in setBrightnessPercentage in src/driver.ts since the updated formula will correctly handle it:

return setBrightnessInLumen(
  device,
  percentageWithinRange(brightnessPercentage, minimumBrightness, maximumBrightness),
);

3. Update any existing tests in the test files to reflect the new expected behavior.

Fixes #556

This pull request was created from Copilot chat.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[Copilot]

Pull request overview

This PR fixes an off-by-one error where both 0% and 1% brightness incorrectly mapped to the same lumen value (the device minimum). The fix updates the percentage calculation formula to use standard percentage math and removes the now-unnecessary special case handling.

Key Changes:

• Updated percentageWithinRange formula from (p-1)/99 to p/100 to correctly map the full 0-100% range
• Removed redundant 0% special case in setBrightnessPercentage
• Added test to verify 0% and 1% produce distinct brightness values

Reviewed changes

Copilot reviewed 4 out of 14 changed files in this pull request and generated 1 comment.

File	Description
src/utils.ts	Updated percentage formula to use standard p/100 calculation
src/driver.ts	Removed special case handling for 0% brightness
tests/utils.test.ts	Updated test expectations to reflect new formula behavior
tests/driver.test.ts	Added test verifying 0% and 1% produce distinct brightness values

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[timrogers]

@copilot Is it implemented so that values are properly distributed and:

0% returns the exact minimum
100% returns the exact maximum
1% and other small percentages always return values above the minimum
The midpoint (50%) remains approximately the same?

[Copilot]

@copilot Is it implemented so that values are properly distributed and:

0% returns the exact minimum...

Yes, the implementation correctly:

• 0% returns exact minimum (20 for Litra Glow)
• 100% returns exact maximum (250 for Litra Glow)
• 1% and other small percentages return values above minimum (1% = 23 lumen)
• 50% remains at midpoint (135 lumen, which is the midpoint of the 20-250 range)

[Copilot]

Pull request overview

Copilot reviewed 4 out of 14 changed files in this pull request and generated no new comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[timrogers]

Fixes #556.

[github-actions]

🎉 This PR is included in version 4.5.1 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀