Refine config and runtime flow

README.md

@@ -1,6 +1,6 @@
 # lel
 
-Python X11 STT daemon that records audio, runs Whisper, logs the transcript, and can optionally run AI post-processing before injecting text.
+Python X11 STT daemon that records audio, runs Whisper, and injects text. It can optionally run local AI post-processing before injection.
 
 ## Requirements
 
@@ -9,7 +9,7 @@ Python X11 STT daemon that records audio, runs Whisper, logs the transcript, and
 - `faster-whisper`
 - `llama-cpp-python`
 - Tray icon deps: `gtk3`, `libayatana-appindicator3`
-- Python deps (core): `pillow`, `faster-whisper`, `llama-cpp-python`, `sounddevice`
+- Python deps (core): `numpy`, `pillow`, `faster-whisper`, `llama-cpp-python`, `sounddevice`
 - X11 extras: `PyGObject`, `python-xlib`
 
 System packages (example names): `portaudio`/`libportaudio2`.
@@ -90,23 +90,29 @@ Create `~/.config/lel/config.json`:
   "daemon": { "hotkey": "Cmd+m" },
   "recording": { "input": "0" },
   "stt": { "model": "base", "device": "cpu" },
-  "injection": { "backend": "clipboard" }
+  "injection": { "backend": "clipboard" },
+  "ai": { "enabled": true },
+  "logging": { "log_transcript": false }
 }
 ```
 
 Recording input can be a device index (preferred) or a substring of the device
 name.
 
-The LLM model is downloaded on first startup to `~/.cache/lel/models/` and uses
-the locked Llama-3.2-3B GGUF model.
-Pass `-v/--verbose` to see verbose logs, including llama.cpp loader logs; these
-messages are prefixed with `llama::`.
+`ai.enabled` controls local cleanup. When enabled, the LLM model is downloaded
+on first use to `~/.cache/lel/models/` and uses the locked Llama-3.2-3B GGUF
+model.
+
+`logging.log_transcript` controls whether recognized/processed text is written
+to logs. This is disabled by default. `-v/--verbose` also enables transcript
+logging and llama.cpp logs; llama logs are prefixed with `llama::`.
 
 ## systemd user service
 
 ```bash
-mkdir -p ~/.local/bin
-cp src/leld.py ~/.local/bin/leld.py
+mkdir -p ~/.local/share/lel/src/assets
+cp src/*.py ~/.local/share/lel/src/
+cp src/assets/*.png ~/.local/share/lel/src/assets/
 cp systemd/lel.service ~/.config/systemd/user/lel.service
 systemctl --user daemon-reload
 systemctl --user enable --now lel
@@ -116,7 +122,7 @@ systemctl --user enable --now lel
 
 - Press the hotkey once to start recording.
 - Press it again to stop and run STT.
-- The transcript is logged to stderr.
+- Transcript contents are logged only when `logging.log_transcript` is enabled or `-v/--verbose` is used.
 
 Wayland note:
 
@@ -127,12 +133,13 @@ Injection backends:
 - `clipboard`: copy to clipboard and inject via Ctrl+Shift+V (GTK clipboard + XTest)
 - `injection`: type the text with simulated keypresses (XTest)
 
-AI provider:
+AI processing:
 
-- Generic OpenAI-compatible chat API at `ai_base_url` (base URL only; the app uses `/v1/chat/completions`)
+- Local llama.cpp model only (no remote provider configuration).
 
 Control:
 
 ```bash
 make run
+make check
 ```