tune: small.en default, vad 700ms, lighter command color, lean inject lines

default model -> small.en (english-only small; better english accuracy, same ~1s
latency; .en variants added to the validator). raise [vad].silence_ms 500 -> 700
(500 cut off too early). command words now brightblue (lighter/cyan-ish) instead of
dark blue. drop the redundant target from injection lines — the [session] prefix
already names it, so e.g. '[claude-testing] typed ...' not '... sticky claude-testing
-> typed ...'.

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

config.toml

@@ -21,11 +21,12 @@ mode = "listen"
 ptt_key = "space"
 
 [stt]
-# faster-whisper model size. "small" is the default — snappy (~1s/command on a strong
-# cpu) and good enough with the initial_prompt biasing + lenient wake matching.
-# "medium" is more accurate on the coined wake word but ~3x slower (noticeable lag);
-# "large-v3" is most accurate and slowest. bump only if recognition is poor.
-model = "small"
+# faster-whisper model size. "small.en" is the default — the English-only small model
+# (~1s/command on a strong cpu, more accurate on english than multilingual "small" at
+# the same speed). "medium"/"medium.en" are more accurate but ~3x slower (noticeable
+# lag); "large-v3" is most accurate and slowest. drop to "base.en" for max snappiness
+# (less accurate). bump only if recognition is poor.
+model = "small.en"
 language = "en"
 # mic device: "auto", or a sounddevice device index (integer) / substring of a
 # device name. run `claudedo test-audio` to list devices.
@@ -47,7 +48,7 @@ min_utterance = 0.3
 # onset and ends after this much trailing silence — the natural end of an utterance.
 # a real pause both ends the command AND separates it from following chatter (the
 # chatter becomes a separate capture that the wake gate then discards).
-silence_ms = 500
+silence_ms = 700
 # hard cap so continuous noise can't record forever.
 max_seconds = 10.0
 

src/claudedo/config.py

@@ -17,7 +17,10 @@ except ModuleNotFoundError:
 log = logging.getLogger(__name__)
 
 _VALID_MODES = ("listen", "ptt")
-_VALID_MODELS = ("tiny", "base", "small", "medium", "large-v2", "large-v3")
+_VALID_MODELS = (
+    "tiny", "base", "small", "medium", "large-v1", "large-v2", "large-v3",
+    "tiny.en", "base.en", "small.en", "medium.en",
+)
 
 DEFAULT_CONFIG_PATHS = (
     Path(os.environ.get("CLAUDEDO_CONFIG", "")) if os.environ.get("CLAUDEDO_CONFIG") else None,
@@ -99,7 +102,7 @@ def load_config(explicit: str | os.PathLike | None = None) -> Config:
     if mode not in _VALID_MODES:
         raise ConfigError(f"[input].mode must be one of {_VALID_MODES}, got {mode!r}")
 
-    model = _require(raw, "stt", "model", (str,), "small")
+    model = _require(raw, "stt", "model", (str,), "small.en")
     if model not in _VALID_MODELS:
         log.warning("unknown stt model %r — passing through to faster-whisper", model)
 
@@ -114,7 +117,7 @@ def load_config(explicit: str | os.PathLike | None = None) -> Config:
         samplerate=int(_require(raw, "audio", "samplerate", (int,), 16000)),
         channels=int(_require(raw, "audio", "channels", (int,), 1)),
         silence_threshold=float(_require(raw, "audio", "silence_threshold", (int, float), 0.012)),
-        vad_silence_ms=int(_require(raw, "vad", "silence_ms", (int,), 500)),
+        vad_silence_ms=int(_require(raw, "vad", "silence_ms", (int,), 700)),
         vad_max_seconds=float(_require(raw, "vad", "max_seconds", (int, float), 10.0)),
         min_utterance=float(_require(raw, "audio", "min_utterance", (int, float), 0.3)),
         type_autosend=bool(_require(raw, "behavior", "type_autosend", (bool,), False)),

src/claudedo/console.py

@@ -19,6 +19,7 @@ _COLORS = {
     "yellow": "\033[33m",
     "cyan": "\033[36m",
     "blue": "\033[34m",
+    "brightblue": "\033[94m",
     "dim": "\033[2m",
     "bold": "\033[1m",
 }

src/claudedo/daemon.py

@@ -179,7 +179,7 @@ class Daemon:
                            "green")
 
         def blue(s):
-            return self._console.paint(s, "blue")
+            return self._console.paint(s, "brightblue")
         if action.name == "mode":
             new_mode = str(action.arg)
             if new_mode != self.mode:
@@ -219,14 +219,14 @@ class Daemon:
             self._console.emit(VOICE, f'heard "{transcript}" -> {reason} -> '
                                f'{self._describe(action)} did nothing', "red")
             return
-        self._inject(session, transcript, reason, action)
+        self._inject(session, action)
 
-    def _inject(self, session: str, transcript: str, reason: str, action) -> None:
+    def _inject(self, session: str, action) -> None:
         """run a resolved command against `session`, tracking the uncommitted-input
         buffer so backspace/erase delete only back to the last submit boundary.
 
-        the 'heard ...' echo is already printed by _handle; these lines report the
-        target (reason) and the keystrokes actually injected.
+        the 'heard ...' echo is already printed by _handle and the [session] prefix
+        names the target, so these lines just report the keystrokes injected.
         """
         name = action.name
 
@@ -237,34 +237,34 @@ class Daemon:
             if self.config.type_autosend:
                 inject.send_named(session, inject.keys.SUBMIT)
                 self._pending[session] = 0
-            self._console.emit(session, f"{reason} -> typed {text!r}"
+            self._console.emit(session, f"typed {text!r}"
                                + (" + send" if self.config.type_autosend else ""), "green")
             return
         if name == "space":
             n = int(action.arg)
             inject.perform(session, action)
             self._pending[session] = self._pending.get(session, 0) + n
-            self._console.emit(session, f"{reason} -> space x{n}", "green")
+            self._console.emit(session, f"space x{n}", "green")
             return
         if name == "backspace":
             n = int(action.arg)
             if n:
                 inject.perform(session, action)
                 self._pending[session] = max(0, self._pending.get(session, 0) - n)
-            self._console.emit(session, f"{reason} -> backspace x{n}", "green")
+            self._console.emit(session, f"backspace x{n}", "green")
             return
         if name == "erase":
             n = self._pending.get(session, 0)
             if n:
                 inject.perform(session, grammar.Action("erase", n))
                 self._pending[session] = 0
-            self._console.emit(session, f"{reason} -> erase x{n} (to last boundary)", "green")
+            self._console.emit(session, f"erase x{n} (to last boundary)", "green")
             return
 
         inject.perform(session, action)
         if name == "submit":
             self._pending[session] = 0
-        self._console.emit(session, f"{reason} -> injected {self._describe(action)}", "green")
+        self._console.emit(session, f"injected {self._describe(action)}", "green")
 
     def _timing(self) -> str:
         """compact STT latency suffix for heard lines (transcribe ms on audio secs)"""