Document Copilot effectiveness patterns in copilot-instructions.md

[Copilot]

GitHub Copilot instructions lacked guidance on which CX Terminal components benefit most from AI assistance versus requiring manual review.

Changes

Added "What Copilot is Best At Working On" section to .github/copilot-instructions.md:

• High-value areas (⭐⭐⭐): AI agent development, voice/audio pipeline, learning/ML components, Lua API bindings (15 crates), test coverage
• Moderate-value areas (⭐⭐): Rendering/UI logic, protocol/IPC layer, CLI command implementation
• Caution areas (❌): Security-critical code, cryptographic operations, core terminal emulation
• Usage patterns: When to trust vs. ignore Copilot suggestions, specific code patterns that work well

Impact

Developers can now:

• Focus Copilot on repetitive patterns (agent traits, FFI bindings, test boilerplate)
• Apply manual review where required (validation logic, auth flows, crypto)
• Use project-specific patterns effectively (Tokio async, anyhow::Result, Serde serialization)

Example guidance provided:

// High-value: Let Copilot generate agent implementations
impl Agent for NewAgent {
    async fn execute() { /* Copilot excels here */ }
}

// Caution: Manual review required
fn validate_command(input: &str) -> Result<SafeCommand> {
    /* Security-critical - always review */
}

Original prompt

What is copilot the best at working on

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

• 🔍 Trigger a full review

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[Copilot]

Pull request overview

This PR adds comprehensive guidance on where GitHub Copilot provides the most value in the CX Terminal codebase, helping developers leverage AI assistance effectively while maintaining security and code quality.

Changes:

• Added "What Copilot is Best At Working On" section documenting high-value areas (AI agents, voice/audio, ML, Lua bindings, testing), moderate-value areas (rendering, IPC, CLI), and caution areas (security, crypto, terminal emulation)
• Included optimal usage patterns and when to trust vs. ignore Copilot suggestions
• Provided concrete examples of project-specific patterns that work well with AI assistance

[Copilot]

The voice/audio pipeline section may be inconsistent with the actual codebase. The PR description and metadata reference 'CX Terminal' and Rust/WezTerm architecture, but the project overview describes 'CX Linux' as a Python-based OS layer with a CLI tool. Verify that a voice/ module with cpal audio capture actually exists in this repository before documenting it as a high-value Copilot area.

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud