vllm-mlx

Subprocess safety, GitHub CLI integration, retry logic, authentication, rate limiting, and timeout handling. Use when integrating external APIs or CLI tools. TRIGGER when: subprocess, gh cli, API call, retry logic, rate limiting, authentication. DO NOT TRIGGER when: internal function calls, pure Python logic, config file edits.

Two-tier design, progressive enhancement, non-blocking patterns, and security-first architecture for Python libraries. Use when creating or refactoring Python libraries. TRIGGER when: library design, module architecture, reusable component, two-tier. DO NOT TRIGGER when: simple scripts, config files, documentation-only changes.

JSON persistence, atomic writes, file locking, crash recovery, and state versioning patterns. Use when implementing stateful libraries or features requiring persistent state. TRIGGER when: state persistence, atomic write, file locking, crash recovery, checkpoint. DO NOT TRIGGER when: stateless utilities, pure functions, config reads, documentation.

GenAI-first testing with structural assertions, congruence validation, and tier-based test structure. Use when writing tests, setting up test infrastructure, or validating coverage. TRIGGER when: test, pytest, coverage, TDD, test patterns, congruence, validation. DO NOT TRIGGER when: production code implementation, documentation, config-only changes.