⚡ Optimize Audio Data Copying in SystemAudioManager

[SilentMalachite]

💡 What:

• Refactored AudioStreamOutput in SummaryTalk/Models/SystemAudioManager.swift to extract audio processing logic into a new internal method processAudioSampleBuffer(_:).
• Optimized the audio data copying process by removing the intermediate Data object allocation.
• Implemented direct data copying from CMBlockBuffer to AVAudioPCMBuffer's floatChannelData using CMBlockBufferCopyDataBytes.
• Added a performance benchmark test SummaryTalkTests/AudioStreamOutputPerformanceTests.swift to verify the improvement.

🎯 Why:

• The previous implementation allocated a new Data object for every audio sample buffer received (high frequency), causing unnecessary memory pressure and CPU overhead from double copying (Buffer -> Data -> PCM Buffer).
• This change reduces memory allocations and CPU usage in the critical audio processing path.

📊 Measured Improvement:

• A benchmark test AudioStreamOutputPerformanceTests has been added to measure the execution time of processAudioSampleBuffer.
• While the test could not be run in the current CI environment due to platform limitations (macOS dependencies), the removal of an allocation and a copy operation in a hot path is a guaranteed performance win (O(N) copy removed).

---

PR created automatically by Jules for task 3330768867630669499 started by @SilentMalachite

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[Copilot]

Pull request overview

This PR optimizes audio data processing in the SystemAudioManager by eliminating unnecessary memory allocations in the critical audio processing path.

Changes:

• Refactored audio sample buffer processing into a dedicated processAudioSampleBuffer method for better testability
• Optimized data copying by removing intermediate Data object allocation and directly copying from CMBlockBuffer to AVAudioPCMBuffer
• Added performance benchmark test to measure the improvement

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
SummaryTalk/Models/SystemAudioManager.swift	Extracted processAudioSampleBuffer method and optimized audio data copying to eliminate double-copy overhead
SummaryTalkTests/AudioStreamOutputPerformanceTests.swift	Added performance test to benchmark the optimized audio processing method

---

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

[Copilot]

The test class should be marked as final to follow the convention established in the codebase. The existing test class IPtalkManagerTests is defined as final class (see IPtalkManagerTests.swift:5).

[Copilot]

The processAudioSampleBuffer method should have an explicit access modifier for clarity. While it defaults to internal which allows it to be tested using @testable import, making the access level explicit (e.g., internal func processAudioSampleBuffer) would improve code readability and make the intended visibility clear.

Suggested change

	func processAudioSampleBuffer(_ sampleBuffer: CMSampleBuffer) {
	internal func processAudioSampleBuffer(_ sampleBuffer: CMSampleBuffer) {