.gitignore

@@ -1,5 +1,4 @@
 CLAUDE.md
-COMPACT.md
 
 __pycache__/
 *.pyc

README.md

@@ -11,7 +11,7 @@ hands-free while another window (a game) is focused.
 It exists because Claude Code's native `/voice` is hardcoded-blocked in WSL (it
 assumes WSL has no audio). Modern WSL2 + WSLg *does* have working mic input via
 PulseAudio/RDP. `claudedo` captures the mic itself, transcribes on-device, and drives
-Claude Code over tmux — fully local and private. You run it in a terminal you watch.
+Claude Code over tmux — fully local, private, backgroundable.
 
 ## How it works
 
@@ -20,11 +20,9 @@ mic (WSLg/PulseAudio RDPSource)
   -> sounddevice capture
   -> faster-whisper (local STT, on-device)
   -> wake gate: utterance must start with a wake phrase, else DISCARD locally
-  -> grammar match (yes/no/one..four/approve/deny/send/type/space/backspace/erase/
+  -> grammar match (yes/no/one..four/approve/deny/send/type/mode/set/target/cancel)
-                    mode/set/target/unset/list/cancel)
+  -> resolve target session (~/.claude-active)
-  -> resolve target session (one-shot > sticky ~/.claude-active > auto/none)
   -> tmux send-keys -t <session> "<keys>"
-  -> log the action to the watched terminal ([session]/[SYSTEM]/[VOICE], colored)
 ```
 
 **Privacy by construction.** STT runs on-device. In listen mode, any speech that
@@ -64,19 +62,16 @@ claudedo test-audio
 ## Usage
 
 **Run it in a terminal you watch — that's the product.** You launch `claudedo
-start` and it drops into a visible listen loop (pass `--check` to run a mic check
+start`, it does a quick mic check, then drops into a visible listen loop that prints
-first). Each utterance prints a timestamped, colored line — `HH:MM:SS [claude-libs]
+`heard → matched → sent` for every utterance. That terminal is your
-heard "…" →
+recognition/action console; you attach to the `claude-<name>` session in another pane
-typed 'fix'` (green for injected, red for drops, `[SYSTEM]`/`[VOICE]` for state and
+to watch the keystrokes land. There is no backgrounding/daemon mode — the whole point
-recognition). That terminal is your recognition/action console; you attach to the
+is the console you read.
-`claude-<name>` session in another pane to watch the keystrokes land. It runs in the
-foreground by design — the console is the point — though `claudedo stop` can signal a
-stray instance.
 
 ```bash
-claudedo start            # the visible listen loop (listen mode default; no mic check)
+claudedo start            # mic-check, then the visible listen loop (listen mode default)
-claudedo start --check    # run a mic check before listening
 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 set <name>       # set the sticky target -> claude-<name> (alias: switch)
@@ -102,12 +97,9 @@ Switch at runtime by voice: "claudedo mode listen" / "claudedo mode ptt".
 
 ## Command grammar
 
-Wake phrases (listen mode), fuzzy-matched. The default list is **"claudedo"**,
+Wake phrases (listen mode), fuzzy-matched: **"claudedo"**, **"hey claude"**.
-**"claude do"**, **"hey claude"**, **"ok claude"**, **"okay claude"** — Whisper has
+"claudedo" is a coined word, so the matcher is lenient (accepts "claude do",
-no token for the coined word "claudedo" and renders it as real words ("claude do"),
+"clauddo", "cloud do", …). In PTT mode the wake phrase is optional.
-so that spelling is listed explicitly. Matching is lenient (case/space-insensitive).
-Add the spellings you actually see (turn on `print_heard` to find them). In PTT mode
-the wake phrase is optional.
 
 | Say | Does |
 |---|---|
@@ -116,10 +108,9 @@ the wake phrase is optional.
 | `approve` / `deny` | allow / deny a permission prompt |
 | `send` / `enter` | submit (Enter) |
 | `type <phrase>` | insert literal text, **no** submit (read-before-send; say "send") |
-| `space [<n>]` (also `add [a] space`, `insert <n> spaces`) | insert n spaces (default 1) |
+| `space [<n>]` | insert n spaces (default 1) |
 | `backspace [<n>]` (alias `delete`) | delete n chars (default 1), capped at the last submit boundary |
 | `erase` (alias `clear`/`wipe`) | delete everything typed since the last submit/boundary |
-| `debug <text>` (alias `echo`) | just print what you said to the console (test wake/STT; injects nothing) |
 | `mode ptt` / `mode listen` | switch input mode |
 | `set <name>` (alias `sticky`/`switch`) | set the **sticky** target → `claude-<name>` (persists) |
 | `target <name> <command>` | **one-shot** override: run that command on `claude-<name>` for this utterance only; sticky default unchanged |
@@ -130,10 +121,8 @@ the wake phrase is optional.
 Optional filler (`select` / `use` / `choose`) may precede any command and is ignored:
 `select yes` and `use yes` behave like `yes`. (`select 1` is still the select command.)
 
-When no sticky target is set, a bare command does nothing and asks you to `set` one
+When no sticky target is set, a bare command auto-targets the **only** running
-(the default). Set `auto_target = true` to instead auto-use the single running
+`claude-*` session; if several are running it does nothing and asks you to `set` one.
-`claude-*` session when there's exactly one; with several running it always does
-nothing and asks you to `set` one.
 
 Number words are normalized to digits before matching ("one"/"won" → 1).
 
@@ -146,9 +135,9 @@ A `target <name>` voice command is a **one-shot** that does NOT touch the sticky
 default — it routes a single command and the next bare command reverts to sticky.
 
 Resolution order (one place — `target.resolve()`): one-shot if present →
-sticky if set and the session exists → else, only if `auto_target = true`, the single
+sticky if set and the session exists → else the only running `claude-*` session →
-running `claude-*` session → else (default, or zero/several sessions) do nothing and
+else (zero or several) do nothing and say so. It never guesses, and never injects
-say so. It never guesses, and never injects into a nonexistent session.
+into a nonexistent session.
 
 Every name maps to `claude-<name>` through one helper (`target.session_name()`), and
 the cc kit mirrors it exactly — so `cc libs` (shell) and `set libs` (voice) refer
@@ -185,29 +174,19 @@ If Claude Code changes its prompt UI, re-confirm against a live session and upda
 ## Config
 
 Everything tunable lives in [`config.toml`](config.toml): wake phrases, mode + PTT
-key, Whisper model/language/device, `[vad]` endpointing, and `[behavior]`
+key, Whisper model/language/device, audio segmentation thresholds, and `[behavior]`
-(`type_autosend`, fuzzy thresholds, `filler_words`, `auto_target`, `print_heard`).
+(`type_autosend`, `filler_words`, `auto_target`, `print_heard`). The default model is
-The default model is **`medium`** (best accuracy for the coined wake word on a strong
+`small`; bump to `medium` if the coined wake word is recognized poorly. `claudedo -c
-CPU); `small` is faster/less accurate, `large-v3` most accurate. `claudedo -c <path>
+<path> ...` points at a specific config; otherwise it searches `$CLAUDEDO_CONFIG`,
-...` points at a specific config; otherwise it searches `$CLAUDEDO_CONFIG`,
 `~/.config/claudedo/config.toml`, then `./config.toml`.
 
-- **STT biasing.** The transcriber is seeded with an `initial_prompt` built from the
+- **`auto_target`** (default `false`): with no sticky target set and exactly one
-  configured wake phrases + command vocabulary (one source — `grammar.vocabulary()`),
+  `claude-*` session running, `false` makes a bare command do nothing and ask you to
-  so Whisper is conditioned to expect "claudedo" and the command words.
+  `set` one; `true` auto-targets that single session.
-- **Split fuzzy thresholds.** `wake_fuzzy_threshold` (default `0.6`, lenient) vs
+- **`print_heard`** (default `false`, debug): prints non-wake transcripts to the
-  `command_fuzzy_threshold` (default `0.8`, tight). The asymmetry is deliberate: a
+  console so you can see how Whisper renders your wake word. Turn it on to debug
-  false *wake* is cheap (it wakes, finds no command, does nothing), but a false
+  detection, then off. Whisper has no token for "claudedo" — it commonly emits
-  *command* fires the wrong action. Prefer expanding command synonyms over loosening
+  "claude do" or "claude due", both of which are in the default wake list.
-  the command threshold.
-- **`[vad]` endpointing.** Capture starts on speech and ends after `silence_ms`
-  (default 800) of trailing silence — Alexa-style record-until-pause — capped at
-  `max_seconds` (default 10). The pause both ends a command and separates it from
-  following chatter (the chatter is a separate capture the wake gate discards).
-- **`auto_target`** (default `false`): with no sticky target and one session running,
-  `false` does nothing and asks you to `set`; `true` auto-uses that session.
-- **`print_heard`** (default `false`, debug): prints non-wake transcripts so you can
-  see how Whisper renders your wake word, then tune the wake list/threshold.
 
 ## Requirements
 

config.toml

@@ -5,7 +5,7 @@
 # wake phrases for listen mode. fuzzy-matched: case/space-insensitive, lenient on
 # the coined word "claudedo" (whisper renders it inconsistently). number words are
 # normalized to digits before command matching.
-phrases = ["claudedo", "claude do", "hey claude", "ok claude", "okay claude"]
+phrases = ["claudedo", "claude do", "claude due", "hey claude", "ok claude", "okay claude"]
 
 [input]
 # "listen" (default): continuous capture; only acts on utterances that start with a
@@ -21,10 +21,10 @@ mode = "listen"
 ptt_key = "space"
 
 [stt]
-# faster-whisper model size. "medium" is the default — biggest accuracy gain for the
+# faster-whisper model size. "small" is a good accuracy/latency balance for the
-# coined wake word ("claudedo" / "claude do") and fine on a strong cpu. "small" is
+# short command grammar (~sub-second per chunk on a strong cpu). if the coined wake
-# faster but less accurate; "large-v3" is most accurate if medium still struggles.
+# word "claudedo" is recognized poorly, bump to "medium" (slower per chunk).
-model = "medium"
+model = "small"
 language = "en"
 # mic device: "auto", or a sounddevice device index (integer) / substring of a
 # device name. run `claudedo test-audio` to list devices.
@@ -36,30 +36,21 @@ compute = "auto"
 # capture parameters. 16 kHz mono is what whisper expects.
 samplerate = 16000
 channels = 1
-# rms energy below this counts as silence (the VAD onset/endpoint floor).
+# listen-mode silence segmentation: an utterance ends after this many seconds below
+# the rms threshold. keeps latency low without streaming.
 silence_threshold = 0.012
+silence_duration = 0.8
 # ignore utterances shorter than this (clicks, coughs).
 min_utterance = 0.3
-
+# hard cap on a single utterance so a stuck stream can't grow unbounded.
-[vad]
+max_utterance = 15.0
-# Alexa-style record-until-pause endpointing (listen mode). capture starts on speech
-# 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 = 800
-# hard cap so continuous noise can't record forever.
-max_seconds = 10.0
 
 [behavior]
 # dictation never auto-submits: "type <phrase>" inserts literal text only; you say
 # "send" separately to submit (read-before-send).
 type_autosend = false
-# fuzzy match ratios (0..1). the asymmetry is deliberate: a false WAKE is cheap (it
+# fuzzy match ratio (0..1) required to accept a wake phrase / command token.
-# wakes, finds no command, does nothing), so wake is lenient; a false COMMAND fires
+match_threshold = 0.8
-# the WRONG action, so commands stay tight. lower = more lenient = more matches.
-# prefer expanding command synonyms over loosening command_fuzzy_threshold.
-wake_fuzzy_threshold = 0.6
-command_fuzzy_threshold = 0.8
 # optional filler words that may precede a command and are ignored for matching:
 # "select yes" / "use yes" behave like "yes". (a filler word followed by a digit is
 # the select command, e.g. "select 1", and is not dropped.)

install.sh

@@ -94,18 +94,6 @@ mkdir -p "$CONF_DIR"
 install -m 0644 "$REPO_DIR/shell/cc.sh" "$CONF_DIR/cc.sh"
 echo "  wrote $CONF_DIR/cc.sh"
 
-# install config.toml to the standard location so the daemon finds it from any dir.
-# never clobber an edited user config: copy only if absent, else drop a .new to diff.
-if [ ! -f "$CONF_DIR/config.toml" ]; then
-    install -m 0644 "$REPO_DIR/config.toml" "$CONF_DIR/config.toml"
-    echo "  wrote $CONF_DIR/config.toml"
-elif ! cmp -s "$REPO_DIR/config.toml" "$CONF_DIR/config.toml"; then
-    install -m 0644 "$REPO_DIR/config.toml" "$CONF_DIR/config.toml.new"
-    echo "  kept your $CONF_DIR/config.toml; new default written to config.toml.new (diff to merge)"
-else
-    echo "  $CONF_DIR/config.toml already current"
-fi
-
 # wire EVERY rc that exists (the user may have both zsh and bash).
 wired_any=0
 for RC in "$HOME/.zshrc" "$HOME/.bashrc"; do

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "claudedo"
-version = "0.1.3"
+version = "0.1.2"
 description = "voice-control daemon for claude code (local STT -> tmux send-keys)"
 readme = "README.md"
 requires-python = ">=3.10"

src/claudedo/__init__.py

@@ -1,3 +1,3 @@
 """claudedo — voice-control daemon for claude code (local STT -> tmux send-keys)"""
 
-__version__ = "0.1.3"
+__version__ = "0.1.2"

src/claudedo/__main__.py

@@ -33,12 +33,12 @@ def cmd_start(args: argparse.Namespace) -> int:
     config = _load_or_die(args.config)
     if args.mode:
         config.mode = args.mode
-    if args.check:
+    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` to skip the check",
+            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}).")
@@ -217,8 +217,8 @@ 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("--check", action="store_true",
+    sp.add_argument("--skip-audio-check", action="store_true",
-                    help="run a mic check before listening (off by default)")
+                    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/config.py

@@ -44,12 +44,11 @@ class Config:
     samplerate: int
     channels: int
     silence_threshold: float
-    vad_silence_ms: int
+    silence_duration: float
-    vad_max_seconds: float
     min_utterance: float
+    max_utterance: float
     type_autosend: bool
-    wake_fuzzy_threshold: float
+    match_threshold: float
-    command_fuzzy_threshold: float
     filler_words: tuple[str, ...]
     auto_target: bool
     print_heard: bool
@@ -99,7 +98,7 @@ 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,), "medium")
+    model = _require(raw, "stt", "model", (str,), "small")
     if model not in _VALID_MODELS:
         log.warning("unknown stt model %r — passing through to faster-whisper", model)
 
@@ -114,25 +113,19 @@ 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,), 800)),
+        silence_duration=float(_require(raw, "audio", "silence_duration", (int, float), 0.8)),
-        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)),
+        max_utterance=float(_require(raw, "audio", "max_utterance", (int, float), 15.0)),
         type_autosend=bool(_require(raw, "behavior", "type_autosend", (bool,), False)),
-        wake_fuzzy_threshold=float(_require(raw, "behavior", "wake_fuzzy_threshold", (int, float), 0.6)),
+        match_threshold=float(_require(raw, "behavior", "match_threshold", (int, float), 0.8)),
-        command_fuzzy_threshold=float(_require(raw, "behavior", "command_fuzzy_threshold",
-                                               (int, float), 0.8)),
         filler_words=tuple(_require(raw, "behavior", "filler_words", (list,),
                                     ["select", "use", "choose"])),
         auto_target=bool(_require(raw, "behavior", "auto_target", (bool,), False)),
         print_heard=bool(_require(raw, "behavior", "print_heard", (bool,), False)),
         source_path=path,
     )
-    for label, val in (("wake_fuzzy_threshold", cfg.wake_fuzzy_threshold),
+    if not 0.0 < cfg.match_threshold <= 1.0:
-                       ("command_fuzzy_threshold", cfg.command_fuzzy_threshold)):
+        raise ConfigError("[behavior].match_threshold must be in (0, 1]")
-        if not 0.0 < val <= 1.0:
-            raise ConfigError(f"[behavior].{label} must be in (0, 1]")
-    if cfg.vad_silence_ms <= 0 or cfg.vad_max_seconds <= 0:
-        raise ConfigError("[vad].silence_ms and max_seconds must be positive")
     if cfg.samplerate <= 0 or cfg.channels <= 0:
         raise ConfigError("[audio].samplerate and channels must be positive")
     return cfg

src/claudedo/daemon.py

@@ -136,7 +136,6 @@ class Daemon:
             model=cfg.stt_model, language=cfg.stt_language,
             device=cfg.stt_compute if cfg.stt_compute in ("cpu", "cuda") else "auto",
             compute_type="auto",
-            initial_prompt=grammar.initial_prompt(cfg.wake_phrases),
         )
         if audio.warm_up(cfg.samplerate, cfg.channels, self._device):
             log.info("mic warmed up (source live)")
@@ -152,20 +151,20 @@ class Daemon:
             return audio.record_while(
                 cfg.samplerate, cfg.channels, self._device,
                 held=lambda: not self._ptt.wait_press(self.stopped),
-                max_utterance=cfg.vad_max_seconds, min_utterance=cfg.min_utterance,
+                max_utterance=cfg.max_utterance, min_utterance=cfg.min_utterance,
             )
         return audio.record_until_silence(
             cfg.samplerate, cfg.channels, self._device,
-            silence_threshold=cfg.silence_threshold, silence_duration=cfg.vad_silence_ms / 1000.0,
+            silence_threshold=cfg.silence_threshold, silence_duration=cfg.silence_duration,
-            min_utterance=cfg.min_utterance, max_utterance=cfg.vad_max_seconds,
+            min_utterance=cfg.min_utterance, max_utterance=cfg.max_utterance,
             stop=self.stopped,
         )
 
     def _handle(self, transcript: str) -> None:
         cfg = self.config
         require_wake = self.mode == "listen"
-        parsed = grammar.parse(transcript, cfg.wake_phrases, cfg.wake_fuzzy_threshold,
+        parsed = grammar.parse(transcript, cfg.wake_phrases, cfg.match_threshold, require_wake,
-                               cfg.command_fuzzy_threshold, require_wake, filler=cfg.filler_words)
+                               filler=cfg.filler_words)
         if parsed is None or parsed.action is None:
             self._console.emit(VOICE, f'heard "{transcript}" -> no command matched', "yellow")
             return
@@ -193,9 +192,6 @@ class Daemon:
             sessions = target.list_sessions()
             self._console.emit(SYSTEM, "list -> " + (", ".join(sessions) if sessions else "(none running)"))
             return
-        if action.name == "debug":
-            self._console.emit(VOICE, f'debug: "{action.arg}"', "yellow")
-            return
 
         session, reason = target.resolve(parsed.one_shot, auto_target=cfg.auto_target)
         if session is None:
@@ -261,8 +257,7 @@ class Daemon:
         invariant: non-command speech is discarded, never recorded.
         """
         cfg = self.config
-        return grammar.strip_wake(transcript, cfg.wake_phrases,
+        return grammar.strip_wake(transcript, cfg.wake_phrases, cfg.match_threshold, True) is not None
-                                  cfg.wake_fuzzy_threshold, True) is not None
 
     def _print_startup(self) -> None:
         cfg = self.config

src/claudedo/grammar.py

@@ -33,33 +33,11 @@ _COUNT_WORDS = {
     "sixteen": 16, "seventeen": 17, "eighteen": 18, "nineteen": 19, "twenty": 20,
 }
 
-_YES_VERBS = ("yes", "yeah", "yep", "yup")
-_NO_VERBS = ("no", "nope", "nah")
-_APPROVE_VERBS = ("approve", "allow")
-_DENY_VERBS = ("deny", "reject")
-_SUBMIT_VERBS = ("send", "enter", "submit")
-_CANCEL_VERBS = ("cancel", "escape")
-_TYPE_VERBS = ("type", "dictate", "write")
-_BACKSPACE_VERBS = ("backspace", "delete")
-_SPACE_VERBS = ("space", "spacebar")
-_ADD_VERBS = ("add", "insert")
-_ERASE_VERBS = ("erase", "clear", "wipe")
-_DEBUG_VERBS = ("debug", "echo")
-_MODE_VERBS = ("mode",)
 _STICKY_VERBS = ("set", "sticky", "switch")
 _ONESHOT_VERBS = ("target",)
 _UNSET_VERBS = ("unset", "unsticky")
 _LIST_VERBS = ("list", "sessions")
 _SELECT_VERBS = ("select", "option", "choose", "number")
-
-# every command/synonym word, for biasing the STT toward the vocabulary we expect.
-_COMMAND_WORDS = (
-    _YES_VERBS + _NO_VERBS + _APPROVE_VERBS + _DENY_VERBS + _SUBMIT_VERBS
-    + _CANCEL_VERBS + _TYPE_VERBS + _BACKSPACE_VERBS + _SPACE_VERBS + _ADD_VERBS
-    + _ERASE_VERBS + _DEBUG_VERBS + _MODE_VERBS + _STICKY_VERBS + _ONESHOT_VERBS + _UNSET_VERBS
-    + _LIST_VERBS + _SELECT_VERBS + ("ptt", "listen")
-    + ("one", "two", "three", "four")
-)
 DEFAULT_FILLER = ("select", "use", "choose")
 
 
@@ -101,26 +79,6 @@ def normalize(text: str) -> str:
     return " ".join(tokens)
 
 
-def vocabulary(wake_phrases: list[str]) -> list[str]:
-    """the wake + command vocabulary, deduped in first-seen order.
-
-    single source for biasing the STT: the same wake phrases the matcher uses plus
-    every command/synonym word in _COMMAND_WORDS. no separate hardcoded copy.
-    """
-    seen: dict[str, None] = {}
-    for word in list(wake_phrases) + list(_COMMAND_WORDS):
-        key = word.strip()
-        if key and key not in seen:
-            seen[key] = None
-    return list(seen)
-
-
-def initial_prompt(wake_phrases: list[str]) -> str:
-    """a comma-joined vocabulary string to pass faster-whisper as initial_prompt,
-    conditioning transcription toward the words we expect (esp. the coined wake)"""
-    return ", ".join(vocabulary(wake_phrases))
-
-
 def _ratio(a: str, b: str) -> float:
     return SequenceMatcher(None, a, b).ratio()
 
@@ -205,42 +163,34 @@ def match_command(remainder: str, threshold: float) -> Action | None:
     if head in _INDEX_WORDS:
         return Action("select", _INDEX_WORDS[head])
 
-    if _fuzzy_in(head, _YES_VERBS, threshold):
+    if _fuzzy_in(head, ("yes", "yeah", "yep", "yup"), threshold):
         return Action("yes")
-    if _fuzzy_in(head, _NO_VERBS, threshold):
+    if _fuzzy_in(head, ("no", "nope", "nah"), threshold):
         return Action("no")
-    if _fuzzy_in(head, _APPROVE_VERBS, threshold):
+    if _fuzzy_in(head, ("approve", "allow"), threshold):
         return Action("approve")
-    if _fuzzy_in(head, _DENY_VERBS, threshold):
+    if _fuzzy_in(head, ("deny", "reject"), threshold):
         return Action("deny")
-    if _fuzzy_in(head, _SUBMIT_VERBS, threshold):
+    if _fuzzy_in(head, ("send", "enter", "submit"), threshold):
         return Action("submit")
-    if _fuzzy_in(head, _CANCEL_VERBS, threshold):
+    if _fuzzy_in(head, ("cancel", "escape"), threshold):
         return Action("cancel")
 
     if _fuzzy_in(head, _SELECT_VERBS, threshold) and rest and rest[0] in _INDEX_WORDS:
         return Action("select", _INDEX_WORDS[rest[0]])
 
-    if _fuzzy_in(head, _TYPE_VERBS, threshold):
+    if _fuzzy_in(head, ("type", "dictate", "write"), threshold):
         text = " ".join(rest).strip()
         return Action("type", text) if text else None
 
-    if _fuzzy_in(head, _BACKSPACE_VERBS, threshold):
+    if _fuzzy_in(head, ("backspace", "delete"), threshold):
         return Action("backspace", _leading_count(rest, default=1))
-    if _fuzzy_in(head, _SPACE_VERBS, threshold):
+    if _fuzzy_in(head, ("space",), threshold):
         return Action("space", _leading_count(rest, default=1))
-    if _fuzzy_in(head, _ADD_VERBS, threshold) and rest:
+    if _fuzzy_in(head, ("erase", "clear", "wipe"), threshold):
-        tail = [t for t in rest if t not in ("a", "an")]
-        if any(_fuzzy_in(t, ("space", "spaces"), threshold) for t in tail):
-            count = next((int(t) for t in tail if t.isdigit()),
-                         next((_COUNT_WORDS[t] for t in tail if t in _COUNT_WORDS), 1))
-            return Action("space", count)
-    if _fuzzy_in(head, _ERASE_VERBS, threshold):
         return Action("erase")
-    if _fuzzy_in(head, _DEBUG_VERBS, threshold):
-        return Action("debug", " ".join(rest).strip())
 
-    if _fuzzy_in(head, _MODE_VERBS, threshold) and rest:
+    if _fuzzy_in(head, ("mode",), threshold) and rest:
         if _fuzzy_in(rest[0], ("ptt",), threshold) or "push" in rest[0]:
             return Action("mode", "ptt")
         if _fuzzy_in(rest[0], ("listen",), threshold):
@@ -271,28 +221,24 @@ def _strip_filler(tokens: list[str], filler: tuple[str, ...], threshold: float)
     return tokens
 
 
-def parse(transcript: str, wake_phrases: list[str], wake_threshold: float,
+def parse(transcript: str, wake_phrases: list[str], threshold: float,
-          command_threshold: float, require_wake: bool,
+          require_wake: bool, filler: tuple[str, ...] = DEFAULT_FILLER) -> ParsedCommand | None:
-          filler: tuple[str, ...] = DEFAULT_FILLER) -> ParsedCommand | None:
     """full parse: wake gate -> optional one-shot target -> filler -> command.
 
-    wake_threshold gates the wake phrase (lenient — a false wake is cheap, it just
+    returns a ParsedCommand (one_shot, action), or None if the wake gate dropped the
-    finds no command); command_threshold gates the command words (stricter — a false
+    utterance (listen mode, no wake phrase). a ParsedCommand with action=None means a
-    command fires the wrong action). returns a ParsedCommand (one_shot, action), or
+    wake phrase was present but no command matched.
-    None if the wake gate dropped the utterance (listen mode, no wake phrase). a
-    ParsedCommand with action=None means a wake phrase was present but no command
-    matched.
     """
-    remainder = strip_wake(transcript, wake_phrases, wake_threshold, require_wake)
+    remainder = strip_wake(transcript, wake_phrases, threshold, require_wake)
     if remainder is None:
         return None
 
     tokens = remainder.split(" ") if remainder else []
     one_shot: str | None = None
-    if tokens and _fuzzy_in(tokens[0], _ONESHOT_VERBS, command_threshold) and len(tokens) >= 2:
+    if tokens and _fuzzy_in(tokens[0], _ONESHOT_VERBS, threshold) and len(tokens) >= 2:
         one_shot = tokens[1]
         tokens = tokens[2:]
 
-    tokens = _strip_filler(tokens, filler, command_threshold)
+    tokens = _strip_filler(tokens, filler, threshold)
-    action = match_command(" ".join(tokens), command_threshold)
+    action = match_command(" ".join(tokens), threshold)
     return ParsedCommand(one_shot=one_shot, action=action)

src/claudedo/stt.py

@@ -82,9 +82,8 @@ class Transcriber:
     """a loaded faster-whisper model that transcribes float32 mono audio chunks"""
 
     def __init__(self, model: str = "small", language: str = "en", device: str = "auto",
-                 compute_type: str = "auto", initial_prompt: str | None = None) -> None:
+                 compute_type: str = "auto") -> None:
         self.language = language
-        self.initial_prompt = initial_prompt
         self._model = self._load(model, device, compute_type)
         self._warm()
 
@@ -121,7 +120,6 @@ class Transcriber:
             beam_size=1,
             vad_filter=True,
             condition_on_previous_text=False,
-            initial_prompt=self.initial_prompt,
         )
         text = " ".join(seg.text for seg in segments).strip()
         return text