...

bolt_pet/audio/mic.py

@@ -44,6 +44,7 @@ def record_utterance(
     silence_end_sec: float = None,
     max_utterance_s: float = None,
     min_utterance_s: float = None,
+    grace_s: float = None,
     frame_len: int = config.FRAME_LEN,
     sample_rate: int = config.SAMPLE_RATE,
 ) -> Optional[np.ndarray]:
@@ -53,18 +54,24 @@ def record_utterance(
     *should_continue* is polled each frame so a caller can cancel recording
     (e.g. the pet window was closed) without needing threading primitives
     baked into this function.
+
+    *grace_s* is how long to wait for speech to *begin* before giving up.
+    The controller stretches it for follow-up questions, where you're being
+    asked something and need a moment to think rather than having just said
+    the wake word on purpose.
     """
     rms_threshold = config.RMS_THRESHOLD if rms_threshold is None else rms_threshold
     silence_end_sec = config.SILENCE_END_SEC if silence_end_sec is None else silence_end_sec
     max_utterance_s = config.MAX_UTTERANCE_S if max_utterance_s is None else max_utterance_s
     min_utterance_s = config.MIN_UTTERANCE_S if min_utterance_s is None else min_utterance_s
+    grace_s = config.GRACE_SECONDS if grace_s is None else grace_s
 
     frames: list[np.ndarray] = []
     started = False
     silence_frames = 0
     silence_limit = int(silence_end_sec * sample_rate / frame_len)
     max_frames = int(max_utterance_s * sample_rate / frame_len)
-    grace_frames = int(4.0 * sample_rate / frame_len)  # wait up to 4s for speech to begin
+    grace_frames = int(grace_s * sample_rate / frame_len)  # how long to wait for speech to begin
     waited = 0
 
     while should_continue():

bolt_pet/config.py

@@ -78,8 +78,36 @@ RMS_THRESHOLD = int(os.environ.get("VAD_RMS_THRESHOLD", "300"))
 SILENCE_END_SEC = float(os.environ.get("VAD_SILENCE_END_SEC", "1.2"))
 MAX_UTTERANCE_S = float(os.environ.get("VAD_MAX_UTTERANCE_SECONDS", "15"))
 MIN_UTTERANCE_S = float(os.environ.get("VAD_MIN_UTTERANCE_SECONDS", "0.4"))
+# How long to wait for you to *start* talking before giving up on a turn.
+GRACE_SECONDS = float(os.environ.get("VAD_GRACE_SECONDS", "4"))
+
+# ── follow-up listening ─────────────────────────────────────────────────────
+# When a reply ends on a question, the pet keeps listening for the answer
+# instead of dropping back to idle and making you say the wake word again.
+# The grace period is longer than a normal turn's because you were asked
+# something and may need a beat to think. FOLLOW_UP_MAX_TURNS caps how many
+# question-and-answer rounds can chain without you re-triggering it — a stop
+# on runaway loops if the server ends every reply with a question and the mic
+# keeps feeding it noise. 0 means no cap.
+
+FOLLOW_UP_LISTEN = os.environ.get("FOLLOW_UP_LISTEN", "true").lower() in ("1", "true", "yes", "on")
+FOLLOW_UP_MAX_TURNS = int(os.environ.get("FOLLOW_UP_MAX_TURNS", "3"))
+FOLLOW_UP_GRACE_SECONDS = float(os.environ.get("FOLLOW_UP_GRACE_SECONDS", "7"))
 
 COMMAND_TIMEOUT_SECONDS = int(os.environ.get("COMMAND_TIMEOUT_SECONDS", "30"))
+
+# ── sudo password prompts ───────────────────────────────────────────────────
+# The pet has no terminal, so a relayed `sudo` would block on a tty nobody is
+# watching. With this on, bare `sudo` is rewritten to `sudo -A` and the
+# password is collected in a desktop dialog (a real askpass binary if one is
+# installed, otherwise a generated zenity/kdialog wrapper). Turn it off and
+# sudo commands simply fail, which is the safer default if you'd rather Bolt
+# never be able to ask for root at all.
+SUDO_ASKPASS_PROMPT = os.environ.get("SUDO_ASKPASS_PROMPT", "true").lower() in ("1", "true", "yes", "on")
+SUDO_ASKPASS_HELPER = os.environ.get("SUDO_ASKPASS_HELPER", "")  # blank = auto-detect
+# Longer than COMMAND_TIMEOUT_SECONDS because a person has to notice the
+# dialog, read it, and type — 30s is nowhere near enough for that.
+SUDO_COMMAND_TIMEOUT_SECONDS = int(os.environ.get("SUDO_COMMAND_TIMEOUT_SECONDS", "180"))
 HEARTBEAT_INTERVAL_SECONDS = float(os.environ.get("HEARTBEAT_INTERVAL_SECONDS", "60"))
 
 # ── barge-in (interrupt playback while the pet is talking) ──────────────────

bolt_pet/controller.py

@@ -63,6 +63,13 @@ class PetController(QObject):
         self._nap_forced: Optional[bool] = None  # petctl nap on/off overrides the schedule
         self._last_nap_check = 0.0
 
+        # When a reply ends on a question the pet keeps listening for the
+        # answer. _follow_ups counts how many have chained without you
+        # re-triggering, so a server that ends every reply with "?" can't
+        # loop forever off mic noise.
+        self._pending_follow_up = False
+        self._follow_ups = 0
+
         self._last_update_check = 0.0
         self._update_pending = False  # applied on disk, waiting for the restart
 
@@ -200,9 +207,21 @@ class PetController(QObject):
         self._near_misses.observe(score, threshold, time.time())
 
     def _handle_conversation_turn(self) -> None:
+        # A turn you started yourself ends any follow-up chain in progress.
+        following_up, self._pending_follow_up = self._pending_follow_up, False
+        if not following_up:
+            self._follow_ups = 0
+
         self._state.transition(PetState.LISTENING)
-        pcm = mic.record_utterance(self._stream, should_continue=self._should_continue)
+        pcm = mic.record_utterance(
+            self._stream,
+            should_continue=self._should_continue,
+            # Answering a question deserves longer than saying the wake word
+            # on purpose does — you were just asked something.
+            grace_s=config.FOLLOW_UP_GRACE_SECONDS if following_up else None,
+        )
         if pcm is None:
+            self._follow_ups = 0  # silence ends the chain
             self._state.transition(PetState.IDLE)
             return
 
@@ -270,6 +289,9 @@ class PetController(QObject):
             on_error=lambda exc: self.log.emit(f"TTS failed: {exc}"),
             should_stop=should_stop,
         )
+        # Read the scoring history *before* resetting, or the log reports the
+        # blank counters instead of what actually fired.
+        detail = self._barge_in_detail()
         if self._barge_in is not None:
             # Playback fed the pet's own voice into the wake model's rolling
             # window. Clear it before the idle listener starts scoring again,
@@ -278,8 +300,36 @@ class PetController(QObject):
         if not completed:
             # You talked over it — take that as the start of the next turn
             # rather than making you say the wake word again.
-            self.log.emit(f"Interrupted — listening. {self._barge_in_detail()}")
+            self.log.emit(f"Interrupted — listening. {detail}")
+            self._follow_ups = 0  # you're clearly engaged; start the count over
             self._talk_now.set()
+        elif self._should_follow_up(text):
+            self._follow_ups += 1
+            cap = config.FOLLOW_UP_MAX_TURNS
+            self.log.emit(
+                f"Asked a question — listening for your answer "
+                f"({self._follow_ups}{'/' + str(cap) if cap > 0 else ''})."
+            )
+            self._pending_follow_up = True
+            self._talk_now.set()
+
+    def _should_follow_up(self, text: str) -> bool:
+        """Whether *text* leaves the pet waiting on an answer.
+
+        Muted is excluded because mute means "don't listen to me" — an
+        automatic turn would walk straight past it. Napping isn't: quiet
+        hours suppress the pet *starting* something, and a question is only
+        ever asked in reply to you."""
+        if not config.FOLLOW_UP_LISTEN or self._muted:
+            return False
+        if not speech_text.is_question(text):
+            return False
+        # Only worth mentioning the cap on a reply that would otherwise have
+        # kept listening, or it fires on every statement the pet makes.
+        if config.FOLLOW_UP_MAX_TURNS > 0 and self._follow_ups >= config.FOLLOW_UP_MAX_TURNS:
+            self.log.emit("Follow-up limit reached — say the wake word to keep going.")
+            return False
+        return True
 
     def _barge_in_detail(self) -> str:
         """Why the interruption fired, for the log. How far into playback it

bolt_pet/server_client.py

@@ -20,7 +20,7 @@ from typing import Callable, Optional
 
 import requests
 
-from . import config
+from . import config, sudo_askpass
 
 _MAX_RELAY_HOPS = 16
 
@@ -42,12 +42,25 @@ def check_health(timeout: float = 10.0) -> dict:
 def run_local_command(command: str, timeout: int = None) -> str:
     """Execute a command relayed by the server, exactly as bolt_desk.py does —
     "full desktop control" for things like "open firefox" or "how full is my
-    disk". Runs as the current desktop user. See README security notes."""
+    disk". Runs as the current desktop user. See README security notes.
+
+    `sudo` gets special handling: the pet has no terminal, so sudo would sit
+    waiting on a tty that nobody is looking at. With SUDO_ASKPASS_PROMPT on,
+    bare `sudo` becomes `sudo -A` and the password is collected in a desktop
+    dialog you have to answer — which also gives those commands a longer
+    timeout, since a human has to notice the window and type."""
+    env = None
+    if config.SUDO_ASKPASS_PROMPT and sudo_askpass.needs_password_prompt(command):
+        helper = sudo_askpass.find_helper()
+        if helper:
+            env = sudo_askpass.environment(helper)
+            command = sudo_askpass.add_askpass_flag(command)
+            timeout = timeout or config.SUDO_COMMAND_TIMEOUT_SECONDS
     timeout = timeout or config.COMMAND_TIMEOUT_SECONDS
     try:
         completed = subprocess.run(
             command, shell=True, capture_output=True, text=True,
-            timeout=timeout, cwd=str(Path.home()),
+            timeout=timeout, cwd=str(Path.home()), env=env,
         )
         output = (completed.stdout or "") + (completed.stderr or "")
         return f"[exit {completed.returncode}]\n{output}"[:6000]

bolt_pet/speech_text.py

@@ -118,6 +118,22 @@ def for_speech(text: str) -> str:
     return text.strip()
 
 
+def is_question(text: str) -> bool:
+    """True if the reply *ends* by asking the user something — the cue for
+    the pet to keep listening instead of making you say the wake word again.
+
+    Deliberately only looks at the end. A reply that asks something in
+    passing ("What time is it? It's 7:15.") isn't waiting on an answer,
+    whereas one that finishes on a question mark is. The test runs on the
+    spoken form, so a '?' that only exists inside a stripped code block or a
+    URL doesn't count, and trailing decoration (emoji, quotes, brackets) is
+    peeled off first so "Ready to go? 🚀" still reads as a question."""
+    spoken = for_speech(text)
+    while spoken and not (spoken[-1].isalnum() or spoken[-1] == "?"):
+        spoken = spoken[:-1]
+    return spoken.endswith("?")
+
+
 def for_display(text: str) -> str:
     """What the speech bubble shows: markdown syntax removed (the bubble
     can't render it) but emoji and layout-ish punctuation left alone."""

bolt_pet/sudo_askpass.py

@@ -0,0 +1,145 @@
+"""Graphical password prompts for server-relayed `sudo` commands.
+
+The pet has no terminal. When the server relays something like
+`sudo apt update`, sudo tries to read a password from a tty, finds none (or
+finds the terminal the pet was launched from, which you're not looking at),
+and the command fails with no way to answer it.
+
+sudo's own answer to this is SUDO_ASKPASS: with `-A`, it runs a helper
+program and reads the password from the helper's stdout instead of a tty.
+Any GUI prompt that prints what was typed works, so this module finds a real
+askpass binary if one is installed and otherwise generates a one-line wrapper
+around zenity/kdialog, which every desktop has one of.
+
+Worth being clear about what this changes: the prompt is a *feature*, not
+just plumbing. Server-relayed commands already run as your desktop user (see
+server_client.run_local_command); this lets them ask to run as root, and the
+dialog is the only thing standing between "Bolt decided to run sudo" and it
+happening. Leave SUDO_ASKPASS_PROMPT on, and read the dialogs.
+
+The parts that decide *what* to run are pure functions so they're tested
+without a display, a password, or a working sudo.
+"""
+
+from __future__ import annotations
+
+import os
+import re
+import shutil
+import stat
+from pathlib import Path
+from typing import Callable, Optional
+
+from . import config
+
+# Real askpass binaries, in preference order. These are purpose-built for
+# this (they grab the keyboard, hide the input, and don't leave the password
+# in a process argument), so they win over a generated wrapper.
+_KNOWN_HELPERS = (
+    "/usr/bin/ssh-askpass",
+    "/usr/lib/ssh/ssh-askpass",
+    "/usr/lib/openssh/gnome-ssh-askpass3",
+    "/usr/lib/openssh/gnome-ssh-askpass",
+    "/usr/libexec/openssh/ssh-askpass",
+    "/usr/bin/ksshaskpass",
+    "/usr/bin/lxqt-openssh-askpass",
+)
+
+# Dialog tools we can wrap when no askpass binary exists. Each must print the
+# typed password to stdout and nothing else.
+_WRAPPABLE = {
+    "zenity": '{tool} --password --title="Bolt" --text="$1" 2>/dev/null',
+    "kdialog": '{tool} --password "$1" --title "Bolt" 2>/dev/null',
+}
+
+# `sudo` at the start of the command or right after a shell separator, not
+# already carrying a flag. Deliberately conservative: a `sudo` inside a
+# quoted string or a heredoc is left alone, because rewriting it could change
+# what the command means.
+_SUDO = re.compile(r"(^|[;&|]\s*|\n\s*)(sudo)(\s+)(?!-)")
+
+
+def add_askpass_flag(command: str) -> str:
+    """Insert `-A` after each bare `sudo`, so it prompts through the helper
+    instead of a tty. Commands that already pass a flag (`sudo -n`, `sudo -A`,
+    `sudo -u bob`) are left exactly as they are — the caller was explicit."""
+    return _SUDO.sub(r"\1\2 -A\3", command or "")
+
+
+def needs_password_prompt(command: str) -> bool:
+    """True if *command* has a `sudo` that might sit waiting on a dialog.
+    Used to give those commands a longer timeout — 30 seconds is fine for a
+    shell command and nowhere near enough for a human to notice a window,
+    read it, and type a password."""
+    return bool(_SUDO.search(command or ""))
+
+
+def helper_script(tool_path: str) -> str:
+    """The wrapper script for a dialog *tool_path*. sudo passes its prompt
+    ("[sudo] password for maji:") as $1, which is worth showing — it names
+    the user the password is for."""
+    name = Path(tool_path).name
+    body = _WRAPPABLE[name].format(tool=tool_path)
+    return f"#!/bin/sh\n# Generated by bolt-pet. Prints the typed password on stdout for sudo -A.\n{body}\n"
+
+
+def _default_cache_dir() -> Path:
+    base = os.environ.get("XDG_CACHE_HOME") or (Path.home() / ".cache")
+    return Path(base) / "bolt-pet"
+
+
+def find_helper(
+    configured: str = None,
+    is_executable: Callable[[str], bool] = None,
+    which: Callable[[str], Optional[str]] = None,
+    cache_dir: Path = None,
+    write: bool = True,
+) -> Optional[str]:
+    """Path to an askpass helper, or None if the desktop has nothing we can
+    use. Order: whatever SUDO_ASKPASS_HELPER names, then a real askpass
+    binary, then a generated wrapper around zenity/kdialog.
+
+    The lookups are injectable so the resolution order is testable on a box
+    with a different set of these installed than yours."""
+    configured = config.SUDO_ASKPASS_HELPER if configured is None else configured
+    is_executable = is_executable or (lambda path: os.path.isfile(path) and os.access(path, os.X_OK))
+    which = which or shutil.which
+
+    if configured:
+        return configured if is_executable(configured) else None
+
+    for candidate in _KNOWN_HELPERS:
+        if is_executable(candidate):
+            return candidate
+
+    for tool in _WRAPPABLE:
+        tool_path = which(tool)
+        if not tool_path:
+            continue
+        if not write:
+            return tool_path
+        return _write_wrapper(tool_path, cache_dir or _default_cache_dir())
+    return None
+
+
+def _write_wrapper(tool_path: str, cache_dir: Path) -> Optional[str]:
+    """Drop the wrapper script somewhere sudo can execute it. Mode 0700: it
+    isn't secret, but it's a thing that pops up a password box, so nobody
+    else on the machine gets to edit it."""
+    try:
+        cache_dir.mkdir(parents=True, exist_ok=True)
+        script = cache_dir / "askpass.sh"
+        source = helper_script(tool_path)
+        if not script.exists() or script.read_text(encoding="utf-8") != source:
+            script.write_text(source, encoding="utf-8")
+        script.chmod(stat.S_IRWXU)
+        return str(script)
+    except Exception:
+        return None  # no prompt is better than a crashed command relay
+
+
+def environment(helper: str, base: dict = None) -> dict:
+    """The subprocess environment with SUDO_ASKPASS pointed at *helper*."""
+    env = dict(os.environ if base is None else base)
+    env["SUDO_ASKPASS"] = helper
+    return env

bolt_pet/updater.py

@@ -183,6 +183,22 @@ def current_ref(run: GitRunner) -> str:
     return output.strip()
 
 
+def already_at_tag(run: GitRunner, tag: str) -> bool:
+    """True if HEAD is already the commit *tag* points at.
+
+    Guards the loop you get when a release is cut without bumping
+    __version__ in the tagged commit: the checkout succeeds (it's a no-op),
+    the pet restarts, reads the same old __version__, sees the same "newer"
+    tag, and does it again — a restart every check, forever."""
+    code, head = run(["rev-parse", "HEAD"])
+    if code != 0 or not head.strip():
+        return False
+    code, target = run(["rev-parse", f"tags/{tag}^{{commit}}"])
+    if code != 0 or not target.strip():
+        return False  # tag isn't known locally yet, so we're certainly not on it
+    return head.strip() == target.strip()
+
+
 def _requirements_changed(run: GitRunner, before: str, after: str) -> bool:
     code, output = run(["diff", "--name-only", before, after, "--", "requirements.txt"])
     return code == 0 and bool(output.strip())
@@ -236,6 +252,14 @@ def apply_update(
     if code != 0:
         raise UpdateError(f"git fetch failed: {output}")
 
+    if already_at_tag(run, tag):
+        from . import __version__
+
+        raise UpdateError(
+            f"already checked out {tag}, but __version__ still reads {__version__} — "
+            f"bump it in the tagged commit, or every check re-applies the same release"
+        )
+
     code, output = run(["checkout", "--force", f"tags/{tag}"])
     if code != 0:
         raise UpdateError(f"git checkout {tag} failed: {output}")