whisper-local/CLAUDE.md

whisper-local

Lokales Speech-to-Text-Tool: Hotkey halten → Audio aufnehmen → faster-whisper transkribieren → Text einfügen.

Entwicklungsumgebung

• Python 3.13+, Paketmanager: uv (Lock-File: uv.lock)
• Python-Scripts direkt ausführen: uv run python <script.py>
• Tests: uv run pytest (mit pytest-asyncio für async-Tests)
• Starten: uv run whisper-local

Sprache

• Entwicklungs- und Dokumentationssprache: Deutsch (Code-Bezeichner bleiben Englisch)

Architektur

• Plattform-Dispatch via Factory-Funktionen: create_listener() / create_inserter()
• Linux: evdev (Hotkey) + ydotool/wl-copy (Wayland-Inserter)
• Windows: pynput (Hotkey) + pywin32 Clipboard + Ctrl+V (Win32-Inserter)
• Interfaces als typing.Protocol — keine abstrakte Basisklasse

Wichtige Muster

• Hotkey-Key-Namen im evdev-Format (KEY_F12), auch auf Windows — _pynput.py übersetzt intern
• Key-Repeat-Unterdrückung im pynput-Backend: _pressed-Flag verhindert Doppelevents
• Async-Callbacks (on_press, on_release) via asyncio.get_running_loop().call_soon_threadsafe

Konfiguration

• Linux: ~/.config/whisper-local/config.toml
• Windows: %APPDATA%\whisper-local\config.toml
• Vorlage: config.example.toml

Tests

• Plattform-spezifische Tests mit @pytest.mark.skipif(sys.platform != "linux", ...)
• Async-Callbacks mit unittest.mock.AsyncMock mocken

CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

• State your assumptions explicitly. If uncertain, ask.
• If multiple interpretations exist, present them - don't pick silently.
• If a simpler approach exists, say so. Push back when warranted.
• If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

• No features beyond what was asked.
• No abstractions for single-use code.
• No "flexibility" or "configurability" that wasn't requested.
• No error handling for impossible scenarios.
• If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

• Don't "improve" adjacent code, comments, or formatting.
• Don't refactor things that aren't broken.
• Match existing style, even if you'd do it differently.
• If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

• Remove imports/variables/functions that YOUR changes made unused.
• Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

• "Add validation" → "Write tests for invalid inputs, then make them pass"
• "Fix the bug" → "Write a test that reproduces it, then make it pass"
• "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

---

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.