FluidAudio CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

FluidAudio is a Swift framework for local, low-latency audio processing on Apple platforms. It provides speaker diarization, automatic speech recognition (ASR), and voice activity detection (VAD) through open-source models converted to Core ML.

Critical Development Rules

NEVER USE @unchecked Sendable

• Always implement thread-safe code with proper synchronization
• Use actors, @MainActor, or proper locking mechanisms instead
• If you encounter Sendable conformance issues, fix them properly

NEVER CREATE DUMMY MODELS OR SYNTHETIC DATA

• Do not create dummy, mock, or fake models for testing or development
• Do not generate synthetic audio data for testing
• Always use the actual models required by the code
• If model authentication is required, inform the user rather than creating dummy versions

HUGGINGFACE UPLOADS

• Uploading models, datasets, and files to HuggingFace is allowed
• Creating HuggingFace repos is allowed
• Confirm the target repo with the user before uploading

MODEL OPERATIONS - CONSULT BEFORE IMPLEMENTING

• When asked to merge, convert, or modify models:
  • If it seems impossible or there are significant objections, consult the user first
  • If they say proceed, do it immediately without further objections
• Do not create placeholder models or implement alternatives without asking

User Preferences

• Never start responses with positive re-affirming text ("You're absolutely right!", "Good change!", etc.)
• Get straight to the point with technical facts
• For debugging, use print statements and delete them at the end when instructed
• Never create fallbacks or simplified solutions that don't actually solve the problem
• When asked to implement something specific, do it first before explaining why it might not be optimal
• Don't over-do things that aren't asked

Development Guidelines