feat: terminal-run only — drop systemd/autostart, start does mic-check + visible loop

terminal-run is the product, so remove all backgrounding: delete the
claudedo.service unit and autostart.sh, strip the systemd step and the
autostart source-line from install.sh (rc block now sources cc.sh only).

claudedo start now runs a mic check first (warm-up + brief capture, aborts with
guidance if silent; --skip-audio-check to bypass) then drops into a visible
listen loop printing the recognition/action log: a startup banner, then
heard -> matched -> target / injected per utterance, target/mode state changes,
and (listen mode) non-wake speech dropped WITHOUT the transcript per the privacy
invariant.

Signed-off-by: disqualifier <dev@disqualifier.me>

README.md

@@ -61,44 +61,23 @@ claudedo test-audio
 
 ## Usage
 
-**Run it in a terminal you watch** — that's the product. The `claudedo start`
-terminal is your recognition/action console (it logs what it heard, what it matched,
-and what it injected); you attach to the `claude-<name>` session in another pane to
-watch the keystrokes land. Backgrounding (tmux/autostart/systemd, below) is an
-optional extra, not the default — it hides the console you'd otherwise read.
+**Run it in a terminal you watch — that's the product.** You launch `claudedo
+start`, it does a quick mic check, then drops into a visible listen loop that prints
+`heard → matched → sent` for every utterance. That terminal is your
+recognition/action console; you attach to the `claude-<name>` session in another pane
+to watch the keystrokes land. There is no backgrounding/daemon mode — the whole point
+is the console you read.
 
 ```bash
-claudedo start            # run the daemon (foreground; listen mode by default)
+claudedo start            # mic-check, then the visible listen loop (listen mode default)
 claudedo start --mode ptt # push-to-talk instead (desk-only — see Modes)
+claudedo start --skip-audio-check  # skip the pre-listen mic check
 claudedo status           # running? mode? target session?
 claudedo stop             # stop a running daemon
 claudedo switch <name>    # retarget to claude-<name>
 claudedo test-audio       # verify the mic capture path
 ```
 
-If you do want it backgrounded (optional — you lose the live console), run it in its
-own tmux session:
-
-```bash
-tmux new-session -d -s claudedo 'claudedo start'
-```
-
-### Autostart
-
-WSL has no real boot, so autostart is rc-based and **opt-in**. `install.sh` ships
-`~/.config/claudedo/autostart.sh`, which starts the daemon in a `claudedo-daemon`
-tmux session once per WSL session — but only when `CLAUDEDO_AUTOSTART=1` is set.
-Enable it by uncommenting the `export CLAUDEDO_AUTOSTART=1` line in the cc-kit marker
-block of your rc; disable it by re-commenting (or deleting the file). Watch its logs
-with `tmux attach -t claudedo-daemon`.
-
-If your WSL runs systemd (`systemd=true` in `/etc/wsl.conf`), `install.sh` also
-installs an optional user unit — enable it instead with:
-
-```bash
-systemctl --user enable --now claudedo
-```
-
 ### Modes
 
 - **listen (default)** — continuous capture; only acts on utterances that **start

install.sh

@@ -92,8 +92,7 @@ say "installing the cc kit (~/.config/claudedo/cc.sh)"
 CONF_DIR="$HOME/.config/claudedo"
 mkdir -p "$CONF_DIR"
 install -m 0644 "$REPO_DIR/shell/cc.sh" "$CONF_DIR/cc.sh"
-install -m 0644 "$REPO_DIR/shell/autostart.sh" "$CONF_DIR/autostart.sh"
-echo "  wrote $CONF_DIR/cc.sh and autostart.sh"
+echo "  wrote $CONF_DIR/cc.sh"
 
 # wire EVERY rc that exists (the user may have both zsh and bash).
 wired_any=0
@@ -109,9 +108,6 @@ for RC in "$HOME/.zshrc" "$HOME/.bashrc"; do
     cat >> "$RC" <<'CCKIT'
 
 # >>> claudedo cc kit >>>
-# voice-daemon autostart is OPT-IN: uncomment the next line to enable it.
-# export CLAUDEDO_AUTOSTART=1
-[ -f ~/.config/claudedo/autostart.sh ] && source ~/.config/claudedo/autostart.sh
 [ -f ~/.config/claudedo/cc.sh ] && source ~/.config/claudedo/cc.sh
 # <<< claudedo cc kit <<<
 CCKIT
@@ -132,19 +128,7 @@ for RC in "$HOME/.zshrc" "$HOME/.bashrc"; do
     fi
 done
 
-# 7. optional systemd user service (only if systemd-in-WSL is available) ---------
-if [ -d /run/systemd/system ] && systemctl --user show-environment >/dev/null 2>&1; then
-    say "systemd user instance detected — installing optional claudedo.service (NOT enabled)"
-    mkdir -p "$HOME/.config/systemd/user"
-    install -m 0644 "$REPO_DIR/shell/claudedo.service" "$HOME/.config/systemd/user/claudedo.service"
-    systemctl --user daemon-reload 2>/dev/null || true
-    echo "  enable it with:  systemctl --user enable --now claudedo"
-    echo "  (or use the rc-based autostart instead — CLAUDEDO_AUTOSTART=1)"
-else
-    echo "  (no systemd user instance — using rc-based autostart; that's normal on WSL)"
-fi
-
-# 8. tmux settings for reliable send-keys (idempotent ~/.tmux.conf append) -------
+# 7. tmux settings for reliable send-keys (idempotent ~/.tmux.conf append) -------
 say "configuring tmux for reliable send-keys (~/.tmux.conf)"
 TMUX_CONF="$HOME/.tmux.conf"
 TMUX_MARKER="# >>> claudedo tmux >>>"

shell/autostart.sh

@@ -1,18 +0,0 @@
-# claudedo autostart (OPT-IN). starts the voice daemon once per WSL session in its
-# own tmux session, if not already running. WSL has no real boot and usually no
-# systemd, so this rc-based guard matches WSL's "starts when you open a terminal"
-# model. POSIX; safe to source under bash and zsh.
-#
-# this only acts when CLAUDEDO_AUTOSTART=1 is set (the rc marker block gates on it),
-# so sourcing it alone does nothing. to enable: export CLAUDEDO_AUTOSTART=1 before
-# the cc-kit marker block in your rc. to disable: unset it (or remove this file).
-#
-# the daemon runs detached; watch its logs with:  tmux attach -t claudedo-daemon
-
-if [ "${CLAUDEDO_AUTOSTART:-0}" = "1" ]; then
-    if command -v claudedo >/dev/null 2>&1; then
-        if ! tmux has-session -t claudedo-daemon 2>/dev/null; then
-            tmux new-session -d -s claudedo-daemon "claudedo start"
-        fi
-    fi
-fi

shell/claudedo.service

@@ -1,14 +0,0 @@
-[Unit]
-Description=claudedo voice-control daemon for claude code
-Documentation=https://github.com/dsql/claudedo
-After=default.target
-
-[Service]
-Type=simple
-ExecStart=%h/.local/bin/claudedo start
-Restart=on-failure
-RestartSec=3
-Environment=PULSE_SERVER=unix:/mnt/wslg/PulseServer
-
-[Install]
-WantedBy=default.target

src/claudedo/__main__.py

@@ -33,6 +33,15 @@ def cmd_start(args: argparse.Namespace) -> int:
     config = _load_or_die(args.config)
     if args.mode:
         config.mode = args.mode
+    if not args.skip_audio_check:
+        print("checking mic before listening (speak briefly) ...")
+        peak = _probe_mic(config, seconds=2.0, verbose=False)
+        if peak is None or peak < 0.02:
+            print("mic check failed — no usable input.", file=sys.stderr)
+            print("run `claudedo test-audio` to debug; or `claudedo start --skip-audio-check`",
+                  file=sys.stderr)
+            return 1
+        print(f"mic OK (peak {peak:.3f}).")
     try:
         daemon.run_daemon(config)
     except RuntimeError as exc:
@@ -41,6 +50,45 @@ def cmd_start(args: argparse.Namespace) -> int:
     return 0
 
 
+def _probe_mic(config: Config, seconds: float, verbose: bool):
+    """warm up the mic then capture for `seconds`; return peak amplitude or None.
+
+    None signals a hard capture failure (no PortAudio / device error) with guidance
+    already printed; a float (possibly ~0) is a successful capture whose level the
+    caller judges. shared by `start`'s precheck and `test-audio`.
+    """
+    from . import audio as audio_mod
+
+    try:
+        device = audio_mod.resolve_device(config.stt_device)
+        if verbose:
+            print("priming mic (RDPSource resumes from suspend) ...")
+        audio_mod.warm_up(config.samplerate, config.channels, device)
+        if verbose:
+            print(f"capturing {seconds:.0f}s from "
+                  f"device={device if device is not None else 'default'} — speak now ...")
+        chunk = audio_mod.record_while(
+            config.samplerate, config.channels, device,
+            held=_timed_hold(seconds), max_utterance=seconds + 1.0, min_utterance=0.0,
+        )
+    except Exception as exc:
+        print(f"audio capture FAILED: {exc}", file=sys.stderr)
+        print("fix-chain: install.sh apt deps + ~/.asoundrc pulse shim + Windows mic permission",
+              file=sys.stderr)
+        return None
+
+    if chunk is None or chunk.size == 0:
+        print("captured no audio — check mic permission + RDPSource", file=sys.stderr)
+        return None
+
+    peak = float(abs(chunk).max())
+    if verbose:
+        out = Path("/tmp/claudedo_test.wav")
+        _write_wav(out, chunk, config.samplerate)
+        print(f"captured {chunk.size / config.samplerate:.1f}s, peak amplitude {peak:.3f} -> {out}")
+    return peak
+
+
 def cmd_stop(_args: argparse.Namespace) -> int:
     if daemon.stop_running():
         print("sent stop signal to claudedo")
@@ -83,36 +131,24 @@ def cmd_test_audio(args: argparse.Namespace) -> int:
     except FileNotFoundError:
         pass
 
+    from . import audio as audio_mod
+    print("\nsounddevice input devices:")
     try:
-        from . import audio as audio_mod
-        print("\nsounddevice input devices:")
         for idx, dev in enumerate(audio_mod.list_devices()):
             if dev.get("max_input_channels", 0) > 0:
                 print(f"  [{idx}] {dev['name']} ({dev['max_input_channels']}ch)")
-        device = audio_mod.resolve_device(config.stt_device)
-        print("\npriming mic (RDPSource resumes from suspend) ...")
-        audio_mod.warm_up(config.samplerate, config.channels, device)
-        print(f"capturing 3s from device={device if device is not None else 'default'} — speak now ...")
-        chunk = audio_mod.record_while(
-            config.samplerate, config.channels, device,
-            held=_timed_hold(3.0), max_utterance=4.0, min_utterance=0.0,
-        )
     except Exception as exc:
-        print(f"\naudio capture FAILED: {exc}", file=sys.stderr)
-        print("fix-chain: install.sh apt deps + ~/.asoundrc pulse shim + Windows mic permission",
-              file=sys.stderr)
-        return 1
+        print(f"  could not list devices: {exc}", file=sys.stderr)
 
-    if chunk is None or chunk.size == 0:
-        print("captured no audio — check mic permission + RDPSource", file=sys.stderr)
+    peak = _probe_mic(config, seconds=3.0, verbose=True)
+    if peak is None:
         return 1
-
-    out = Path("/tmp/claudedo_test.wav")
-    _write_wav(out, chunk, config.samplerate)
-    peak = float(abs(chunk).max())
-    print(f"captured {chunk.size / config.samplerate:.1f}s, peak amplitude {peak:.3f} -> {out}")
-    if peak < 0.005:
+    if peak < 0.02:
         print("WARNING: near-silent capture — is the mic muted / permission denied?")
+        print("fix-chain: Windows mic permission for desktop apps + a non-Krisp default input;")
+        print("           if still silent, `wsl --shutdown` then reopen to re-attach RDPSource.")
+        return 1
+    print("mic OK.")
     return 0
 
 
@@ -164,6 +200,8 @@ def build_parser() -> argparse.ArgumentParser:
 
     sp = sub.add_parser("start", help="run the daemon (foreground)")
     sp.add_argument("--mode", choices=("listen", "ptt"), help="override input mode")
+    sp.add_argument("--skip-audio-check", action="store_true",
+                    help="skip the pre-listen mic check")
     sp.set_defaults(func=cmd_start)
 
     sub.add_parser("stop", help="stop a running daemon").set_defaults(func=cmd_stop)

src/claudedo/daemon.py

@@ -162,29 +162,67 @@ class Daemon:
         require_wake = self.mode == "listen"
         action = grammar.parse(transcript, cfg.wake_phrases, cfg.match_threshold, require_wake)
         if action is None:
-            log.debug("discarded (no wake/command)")
+            self._emit(f'heard: "{transcript}" -> no command matched')
             return
 
         if action.name == "mode":
             new_mode = str(action.arg)
             if new_mode != self.mode:
                 self.mode = new_mode
-                log.info("mode -> %s", new_mode)
+                self._emit(f"mode -> {new_mode}")
                 self._refresh_state()
             return
         if action.name == "switch":
             session = target.set_target(str(action.arg))
-            log.info("switched target -> %s", session)
+            self._emit(f"target -> {session}")
             self._refresh_state()
             return
 
         session = target.resolve_target()
         if session is None:
+            self._emit(f'heard: "{transcript}" -> matched: {self._describe(action)} '
+                       f'-> ERROR no target session (did nothing)')
             return
+        self._emit(f'heard: "{transcript}" -> matched: {self._describe(action)} -> target {session}')
         if action.name == "type" and not cfg.type_autosend:
             inject.send_literal(session, str(action.arg))
+            self._emit(f"injected: literal {str(action.arg)!r} -> {session}")
             return
         inject.perform(session, action)
+        self._emit(f"injected: {self._describe(action)} -> {session}")
+
+    @staticmethod
+    def _describe(action) -> str:
+        if action.arg is None:
+            return action.name.upper()
+        return f"{action.name.upper()}({action.arg})"
+
+    @staticmethod
+    def _emit(line: str) -> None:
+        """print a recognition/action line to the watched terminal"""
+        print(line, flush=True)
+
+    def _has_wake(self, transcript: str) -> bool:
+        """true if the utterance starts with a wake phrase (listen-mode gate).
+
+        non-wake speech is dropped without ever printing the transcript — the privacy
+        invariant: non-command speech is discarded, never recorded.
+        """
+        cfg = self.config
+        return grammar.strip_wake(transcript, cfg.wake_phrases, cfg.match_threshold, True) is not None
+
+    def _print_startup(self) -> None:
+        cfg = self.config
+        dev = cfg.stt_device if cfg.stt_device != "auto" else "default"
+        target_now = target.read_active() or "(none — run cc to attach)"
+        self._emit("── claudedo ─────────────────────────────────")
+        self._emit(f"  model:   {cfg.stt_model} ({cfg.stt_language})")
+        self._emit(f"  mic:     {dev}")
+        self._emit(f"  mode:    {self.mode}")
+        self._emit(f"  target:  {target_now}")
+        self._emit(f"  wake:    {', '.join(cfg.wake_phrases)}")
+        self._emit("  Ctrl-C to stop")
+        self._emit("─────────────────────────────────────────────")
 
     def _refresh_state(self) -> None:
         write_state(os.getpid(), self.mode, target.read_active())
@@ -197,8 +235,7 @@ class Daemon:
         try:
             self._load()
             self._refresh_state()
-            log.info("claudedo running (mode=%s); say a wake phrase + command", self.mode)
-            print(f"claudedo listening in {self.mode!r} mode — Ctrl-C to stop")
+            self._print_startup()
             while not self._stop:
                 audio_chunk = self._capture()
                 if self._stop:
@@ -208,7 +245,9 @@ class Daemon:
                 transcript = self._transcriber.transcribe(audio_chunk, self.config.samplerate)
                 if not transcript:
                     continue
-                log.debug("heard: %s", transcript)
+                if self.mode == "listen" and not self._has_wake(transcript):
+                    self._emit("dropped: non-wake speech (not recorded)")
+                    continue
                 self._handle(transcript)
         finally:
             PIDFILE.unlink(missing_ok=True)