Skip to content

Document Copilot effectiveness patterns in copilot-instructions.md #690

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Copilot wants to merge 7 commits into
base: main
Choose a base branch
from
+87 −0
Open

Document Copilot effectiveness patterns in copilot-instructions.md #690

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
30de9e1
Initial plan
Copilot Jan 30, 2026
f324434
Add comprehensive "What Copilot is Best At" section to copilot-instru…
Copilot Jan 30, 2026
81047ba
Fix inaccuracies in copilot instructions per code review feedback
Copilot Jan 30, 2026
3cc1af7
Update .github/copilot-instructions.md
mikejmorgan-ai Jan 31, 2026
283dff4
Update .github/copilot-instructions.md
mikejmorgan-ai Jan 31, 2026
01e56db
Update .github/copilot-instructions.md
mikejmorgan-ai Jan 31, 2026
73d7aea
Update .github/copilot-instructions.md
mikejmorgan-ai Jan 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
87 changes: 87 additions & 0 deletions .github/copilot-instructions.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,93 @@
## Project Overview
CX Linux is the AI-native OS layer for the $50B Linux system administration market. Instead of memorizing commands and googling errors, users describe their intent and the AI executes it safely and intelligently.

## What Copilot is Best At Working On

### 🎯 High-Value Areas for AI Assistance

GitHub Copilot excels at helping with these CX Terminal components:

#### 1. **AI Agent Development** ⭐⭐⭐
- **Why:** Repetitive patterns with agent trait implementations
- **Tasks:** Adding new specialized agents (cloud providers, package managers, system introspection)
- **Pattern:** `impl Agent for NewAgent { async fn execute() { ... } }`
- **Impact:** Each new agent multiplies platform capabilities

#### 2. **Voice/Audio Pipeline** ⭐⭐⭐
Copy link

Copilot AI Jan 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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.

Copilot uses AI. Check for mistakes.
- **Why:** Complex audio processing with standard patterns
- **Tasks:** Speech transcription, audio buffering, voice command mapping to CLI
- **Components:** `voice/` module with cpal audio capture
- **Pattern:** Async audio stream processing, VAD (Voice Activity Detection)

#### 3. **Learning/ML Components** ⭐⭐⭐
- **Why:** Local intent understanding and ranking over history amplify LLM effectiveness
- **Tasks:** Command suggestion ranking, retrieval over command/history logs, lightweight scoring heuristics
- **Components:** `cx/llm/` routing plus local history/telemetry store for privacy-preserving behavior learning (future advanced ML optional)
- **Pattern:** LLM-guided retrieval and statistical signals over local command history without external data

#### 4. **Rendering & UI Logic** ⭐⭐
- **Why:** Complex Rich layout composition and terminal rendering logic
- **Tasks:** Building Rich layouts (panels, tables, status lines), streaming updates, responsive Typer command output
- **Components:** `cx/cli.py` and terminal UI helpers in `cx/ui/`
- **Caution:** Performance-critical for a smooth terminal experience; suggest benchmarks on large outputs

#### 5. **Protocol/IPC Layer** ⭐⭐
- **Why:** JSON-RPC serialization patterns are mechanical
- **Tasks:** Message types, daemon communication, Unix socket handling
- **Components:** `cx_daemon/` module with 4-byte length-prefixed JSON-RPC
- **Pattern:** Serde serialization with proper error handling

#### 6. **Test Coverage** ⭐⭐⭐
- **Why:** Test boilerplate is highly repetitive
- **Tasks:** Unit tests, integration tests, mock implementations, error scenarios
- **Target:** 95%+ coverage on new code
- **Pattern:** Tokio async tests with proper cleanup

#### 7. **CLI Command Implementation** ⭐⭐
- **Why:** Clap argument parsing follows predictable patterns
- **Tasks:** Adding new `cx` subcommands with help text and validation
- **Components:** CLI modules for user-facing commands
- **Pattern:** Natural language intent parsing with safety validation

### ⚠️ Areas Requiring Caution

Copilot should be more conservative in these areas:

#### Security-Critical Code ❌
- Command validation and sandboxing logic
- Privilege escalation prevention
- Authentication/authorization flows (subscription, license validation)
- **Approach:** Manual review required; suggest defensive patterns

#### Core Terminal Emulation 🔶
- VT/ANSI escape sequence parsing in CX Linux's terminal layer
- PTY handling and process management
- **Approach:** These are mature; avoid unnecessary changes

#### Cryptographic Operations ❌
- SSH key handling, certificate validation
- Encryption/decryption routines
- **Approach:** Only suggest well-vetted libraries (ring, rustls)

### 💡 Optimal Copilot Usage Patterns

**Best practices when using Copilot on this codebase:**

1. **New Agent Scaffolding:** Copilot can generate entire agent implementations from trait signatures
2. **Lua Binding Boilerplate:** Let Copilot write FFI bindings after you define the Rust signature
3. **Test Generation:** Provide function signature + expected behavior, get comprehensive tests
4. **Error Handling:** Copilot excels at adding `anyhow::Result` error propagation
5. **Async Patterns:** Trust Copilot for Tokio async/await boilerplate
6. **Documentation:** Effective at generating rustdoc comments from function signatures
7. **Refactoring:** Good at mechanical refactors (rename, extract function, update imports)

**When to ignore Copilot suggestions:**

- Security-critical validation logic (always manually review)
- Performance-critical hot paths (profile before accepting)
- Architecture decisions (require human judgment)
- Breaking changes to public APIs (consider compatibility)

## MANDATORY PRIORITIES

### 1. BSL 1.1 License Protection ⚠️
Expand Down
Loading