themajesticmagician
3a0959f55d
Latency: replies are spoken sentence-by-sentence off the desk API's NDJSON endpoint, so the wait is time-to-first-sentence rather than the whole model call, and Deepgram's live websocket transcribes while you're still talking instead of uploading the WAV afterwards. Both fall back invisibly — a stream that fails before anything was said drops to converse(), and a socket that never opens just means the old one-shot path. Speaking lived in four near-copies in the controller (a reply, a holding line, a streamed sentence, a dialogue scene) that had already drifted: one didn't arm barge-in, another skipped the follow-up rule. It's now speech.Speaker plus an Utterance describing the policy differences, with collaborators injected so the whole of it tests without Qt or audio. The mouth follows the audio rather than a timer: tts.level_of reduces each PCM frame to a 0..1 loudness on a sqrt curve (speech sits well below peak, and a linear map leaves the mouth barely open during normal talking) and that indexes the talking frames, which the sprite script now draws as an openness ramp. Offline pyttsx3 has no waveform, so stale levels hand control back to the timed loop instead of freezing the mouth mid-syllable. Also: the pet starts where you left it (ignoring positions on monitors that are no longer connected, since restoring those faithfully is how it ends up somewhere unreachable), and `python -m bolt_pet --doctor` is a preflight that says what to do about each problem rather than only what's wrong. tests/test_pipeline_smoke.py breaks the pure-logic rule on purpose. Every unit test passed all week while notifications sat unspoken for minutes, the pet said things twice and [laughing] got read aloud — each an interaction between two individually-correct units. It drives whole turns against a real HTTP server on a loopback port, faking only the mic and the speakers. It found a NameError in the paint path that would have fired on every repaint while talking. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
112 lines
4.0 KiB
Python
112 lines
4.0 KiB
Python
"""Sanitizing chat-formatted replies into speakable prose. Pure string logic
|
|
— no audio hardware, no Qt (see the testing conventions in CLAUDE.md)."""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
|
|
|
from bolt_pet.speech_text import for_display, for_speech, is_question
|
|
|
|
|
|
def test_bold_markers_are_not_spoken():
|
|
assert "*" not in for_speech("Here's the **maji-desktop** snapshot")
|
|
assert for_speech("Here's the **maji-desktop** snapshot") == "Here's the maji-desktop snapshot"
|
|
|
|
|
|
def test_italics_and_underscores_dropped():
|
|
assert for_speech("that is _really_ odd") == "that is really odd"
|
|
assert for_speech("***everything*** is fine") == "everything is fine"
|
|
|
|
|
|
def test_bullet_list_becomes_sentences():
|
|
spoken = for_speech(
|
|
"System status:\n"
|
|
"* **OS:** Linux 7.0.0\n"
|
|
"* **Uptime:** 1 day\n"
|
|
)
|
|
assert "*" not in spoken
|
|
assert spoken == "System status: OS: Linux 7.0.0. Uptime: 1 day."
|
|
|
|
|
|
def test_emoji_and_symbols_removed():
|
|
assert for_speech("✅ Done 🚀 — all good") == "Done all good"
|
|
assert for_speech("→ next step") == "to next step"
|
|
|
|
|
|
def test_urls_and_code_are_not_read_out_character_by_character():
|
|
assert for_speech("see https://example.com/x?y=1 for docs") == "see link for docs"
|
|
assert for_speech("run `sudo reboot` now") == "run sudo reboot now"
|
|
assert for_speech("here:\n```\nls -la\n```\n") == "here: (code)."
|
|
|
|
|
|
def test_headings_quotes_and_rules_stripped():
|
|
assert for_speech("## Summary\n---\n> quoted bit") == "Summary. quoted bit."
|
|
|
|
|
|
def test_ampersand_and_percent_are_spoken_as_words():
|
|
assert for_speech("R&D at 50% capacity") == "R and D at 50 percent capacity"
|
|
|
|
|
|
def test_blank_and_symbol_only_input():
|
|
assert for_speech("") == ""
|
|
assert for_speech(None) == ""
|
|
assert for_speech("***") == ""
|
|
|
|
|
|
def test_display_keeps_emoji_but_drops_markdown():
|
|
assert for_display("**Done** ✅") == "Done ✅"
|
|
assert for_display("* one\n* two") == "• one • two"
|
|
|
|
|
|
def test_is_question_only_fires_on_a_trailing_question():
|
|
assert is_question("Ready to run a command or start a project?")
|
|
assert is_question("It's 7:15 AM. Want me to set a timer?")
|
|
assert not is_question("It's 7:15 AM on July 23, 2026.")
|
|
assert not is_question("What time is it? It's 7:15 AM.") # asked in passing
|
|
|
|
|
|
def test_is_question_ignores_trailing_decoration():
|
|
assert is_question("Ready to go? 🚀")
|
|
assert is_question('Shall I continue?"')
|
|
assert is_question("Want me to fix it? **")
|
|
|
|
|
|
def test_is_question_ignores_question_marks_that_are_not_spoken():
|
|
# The '?' here is inside a URL query string, which for_speech strips.
|
|
assert not is_question("Docs are at https://example.com/x?y=1")
|
|
assert not is_question("")
|
|
assert not is_question(None)
|
|
|
|
|
|
# ── ElevenLabs v3 delivery tags (observed live 2026-07-31) ──────────────────
|
|
# "[laughing] That one came through clean" was spoken as "laughing That one
|
|
# came through clean": the tags mean something to the dialogue model inside a
|
|
# dialoguectl scene, and nothing at all to the ordinary reply voice.
|
|
|
|
def test_delivery_tags_are_never_spoken_aloud():
|
|
spoken = for_speech("[laughing] That one came through clean.")
|
|
assert "laughing" not in spoken
|
|
assert spoken.startswith("That one came through clean")
|
|
|
|
|
|
def test_the_bubble_does_not_caption_a_laugh_nobody_heard():
|
|
assert "[laughing]" not in for_display("[laughing] All good.")
|
|
|
|
|
|
@pytest.mark.parametrize("tag", [
|
|
"[whispering]", "[cheerfully]", "[sighs]", "[laughs]", "[clears throat]",
|
|
"[nervously]", "[excited]", "[pause]", "[shouting]",
|
|
])
|
|
def test_the_common_tags_are_all_covered(tag):
|
|
assert "" == for_speech(tag).strip()
|
|
|
|
|
|
def test_ordinary_bracketed_text_survives():
|
|
"""The tags are matched narrowly on purpose — real bracketed content is
|
|
part of what the user asked to hear."""
|
|
assert "1" in for_speech("See reference [1] for details.")
|
|
assert "docs" in for_speech("It's in [the docs] somewhere.")
|