Remove log_transcript config and enforce JSON AI output

README.md

@@ -92,7 +92,6 @@ Create `~/.config/lel/config.json`:
   "stt": { "model": "base", "device": "cpu" },
   "injection": { "backend": "clipboard" },
   "ai": { "enabled": true },
-  "logging": { "log_transcript": false },
   "vocabulary": {
     "replacements": [
       { "from": "Martha", "to": "Marta" },
@@ -113,9 +112,9 @@ name.
 AI cleanup is always enabled and uses the locked local Llama-3.2-3B GGUF model
 downloaded to `~/.cache/lel/models/` on first use.
 
-`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::`.
+Use `-v/--verbose` to enable DEBUG logs, including recognized/processed
+transcript text and llama.cpp logs (`llama::` prefix). Without `-v`, logs are
+INFO level.
 
 Vocabulary correction:
 
@@ -152,7 +151,7 @@ systemctl --user enable --now lel
 - Press the hotkey once to start recording.
 - Press it again to stop and run STT.
 - Press `Esc` while recording to cancel without processing.
-- Transcript contents are logged only when `logging.log_transcript` is enabled or `-v/--verbose` is used.
+- Transcript contents are logged only when `-v/--verbose` is used.
 
 Wayland note: