feat: Enhance local command handling and introduce local intents

- Refactor `run_local_command` to manage subprocesses more effectively, ensuring child processes are terminated on timeout.
- Introduce `_terminate` function to handle process group termination and capture output.
- Implement `_command_output` to format command results with a character limit.
- Add local intent recognition in `intents.py` to handle commands like "stop", "go to sleep", and "come here" without server interaction.
- Normalize user input to match local intents while stripping filler words.
- Update tests to cover new local intent functionality and ensure proper command handling.
- Enhance speech processing to handle abbreviations and improve spoken output clarity.

bolt_pet/speech_text.py

@@ -67,6 +67,27 @@ _SPOKEN_SYMBOLS = {
     "=": " equals ",
 }
 
+# Abbreviations a voice spells out letter by letter ("eee gee") because the
+# periods make them look like sentence boundaries. Written out instead — this
+# has to run before _UNSPEAKABLE strips anything, and the trailing \.? keeps
+# "etc" working with or without its period. Word-bounded so "vs" inside a
+# filename is left alone.
+_SPOKEN_ABBREVIATIONS = (
+    (re.compile(r"\be\.g\.?(?=\s|$)", re.IGNORECASE), "for example"),
+    (re.compile(r"\bi\.e\.?(?=\s|$)", re.IGNORECASE), "that is"),
+    (re.compile(r"\betc\.?(?=\s|$)", re.IGNORECASE), "and so on"),
+    (re.compile(r"\bvs\.?(?=\s|$)", re.IGNORECASE), "versus"),
+    (re.compile(r"\baka\b", re.IGNORECASE), "also known as"),
+    (re.compile(r"\bw/(?=\s)", re.IGNORECASE), "with"),
+    # "PR #42" -> "PR number 42"; a bare "#" is markup and _UNSPEAKABLE drops it.
+    (re.compile(r"#(?=\d)"), "number "),
+    # A long option's dashes are punctuation to the eye and syllables to the ear
+    # ("dash dash force"). Only the doubled form: a single hyphen has to survive
+    # for "bolt-pet" and "up-to-date", and requiring a word character after it
+    # keeps a "---" horizontal rule intact for _RULE to strip.
+    (re.compile(r"(?<!\w)--(?=\w)"), ""),
+)
+
 _MULTI_SPACE = re.compile(r"[ \t]+")
 _MULTI_PUNCT = re.compile(r"(?:\s*\.){2,}")
 
@@ -105,6 +126,10 @@ def for_speech(text: str) -> str:
         return ""
     for symbol, spoken in _PRE_SPOKEN_SYMBOLS.items():
         text = text.replace(symbol, spoken)
+    # Before the markdown pass, so "#42" still has its "#" to word and a real
+    # "## Heading" (no digit after the hashes) is left for _HEADING to strip.
+    for pattern, spoken in _SPOKEN_ABBREVIATIONS:
+        text = pattern.sub(spoken, text)
     text = _strip_markdown(text, keep_emoji=False)
     text = _URL.sub(" link ", text)
     text = _TABLE_PIPE.sub(", ", text)
@@ -119,17 +144,21 @@ def for_speech(text: str) -> str:
 
 
 def is_question(text: str) -> bool:
-    """True if the spoken reply contains a question mark — the cue for the
-    pet to keep listening instead of making you say the wake word again.
+    """True if the reply asks the user anything — the cue for the pet to keep
+    listening instead of making you say the wake word again.
 
-    The check 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] in "?."):
-        spoken = spoken[:-1]
-    return "?" in spoken
+    Anywhere in the reply counts, not only the end. An earlier version required
+    a *trailing* '?' on the theory that "What time is it? It's 7:15." isn't
+    waiting on an answer, and that's true of that sentence but wrong far more
+    often: Bolt routinely asks first and then keeps talking ("Want me to fix
+    it? I'd start with the config."), and refusing to listen there is the case
+    that actually costs you a wake word. The cheap failure is the other
+    direction — an unwanted extra listen ends itself on `VAD_GRACE_SECONDS` of
+    silence, and `FOLLOW_UP_MAX_TURNS` caps the chain.
+
+    The test runs on the *spoken* form, so a '?' that only exists inside a
+    stripped code block, a URL, or a markdown link target doesn't count."""
+    return "?" in for_speech(text)
 
 
 def for_display(text: str) -> str: