feat(orchestrator): radio set with CPU-gated speech, noise burst, modes and log (requirement 004)
The hub gates uncached /api/tts renders on the latest W4 host CPU sample (503 busy or unknown, cached lines always served, signed speech.threshold 30 to 90 in steps of 10, speech.gate in /api/state). The page plays a WebAudio squelch-tail burst when no speech plays, offers Auto, Quiet and Silence per browser, and always sounds the MAYDAY, PAN-PAN and SECURITE procedure word. The radio panel becomes a minimalist VHF faceplate with display line, mode buttons, knobs, PTT send and the internet station; the settings dialog loses its radio section. The log gets Sent, Received and All tabs with class, sender, recipient and agent chips plus text search. Decisions 3 and 10 of 004 now state that the procedure word still sounds in Silence. Security: MEDUSA-MEX-SCAN-1167 at orchestrator/kvb_orchestrator/hub.py:126 accepted as a false positive after the round 5 skeptic review and the operator pick of 2026-11-13 (regex hit on rce inside RESOURCES; CpuGate reads host CPU samples, no model). Break risk 6 % is above the 5 % bar; committed and merged on the operator pick of 2026-11-13 for this bundle. 🎯 Fix: 92 % 💥 Break: 6 % 💸 Cost: 100 % ⏱️ Time: 100 % 🛡️ Security: 100 % 🏆 Score: 86 🚦 Gate: ⛔ break 6 % > 5 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
69693ac2bc
commit
acf39255fc
37 files changed
+2480
-356
No files matched your search
@@ -8,13 +8,14 @@ import subprocess
|
||||
import threading
|
||||
import time
|
||||
import wave
|
||||
from collections.abc import Callable
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from .council import HUMAN
|
||||
from .errors import EngineError, ToolError, Unavailable
|
||||
from .fields import TEXT_LIMIT, bounded, decode, expect
|
||||
from .phrasing import SPEECH_LIMIT, SPOKEN_LINE, phrase
|
||||
from .phrasing import PROCEDURE_LINES, SPEECH_LIMIT, SPOKEN_LINE, phrase
|
||||
from .records import digest, read_json
|
||||
from .skill_scripts import SAFE_PATH
|
||||
|
||||
@@ -22,6 +23,7 @@ MODEL_NAME = re.compile(r"[A-Za-z0-9][A-Za-z0-9_.-]{0,127}")
|
||||
SPEAKER_LIMIT = 10000
|
||||
TTS_TIMEOUT = 120
|
||||
TTS_KEEP = 200
|
||||
WORD_CACHE = "word-"
|
||||
STT_RATE = 16000
|
||||
STT_SECONDS = 120
|
||||
STT_LIMIT = 44 + STT_RATE * 2 * STT_SECONDS
|
||||
@@ -141,6 +143,7 @@ class Speech:
|
||||
raise ToolError(f"the operator voice {engines.operator_voice!r} is not installed in {engines.voices}")
|
||||
self.operator = engines.operator_voice if self.voices else ""
|
||||
self.pool = [voice for voice in self.voices if voice != self.operator]
|
||||
self.handed = {self.operator} if self.operator else set()
|
||||
self.speaking = threading.Lock()
|
||||
self.hearing = threading.Lock()
|
||||
self.metering = threading.Lock()
|
||||
@@ -174,7 +177,15 @@ class Speech:
|
||||
return gap or ("" if os.path.isfile(model) else f"the whisper.cpp model {model} is not a file")
|
||||
|
||||
def voice_of(self, key: str) -> str:
|
||||
return voice_of(key, self.pool, self.operator)
|
||||
"""Args:
|
||||
key: the speaker's session id or directory key.
|
||||
|
||||
Returns:
|
||||
The speaker's voice, which /api/tts accepts from then on.
|
||||
"""
|
||||
voice = voice_of(key, self.pool, self.operator)
|
||||
self.handed.add(voice)
|
||||
return voice
|
||||
|
||||
def describe(self) -> dict:
|
||||
operator = self.voice_of(HUMAN)
|
||||
@@ -185,7 +196,15 @@ class Speech:
|
||||
"limit": SPEECH_LIMIT, "rate": STT_RATE, "seconds": STT_SECONDS,
|
||||
}
|
||||
|
||||
def synthesize(self, body: bytes) -> bytes:
|
||||
def synthesize(self, body: bytes, admit: Callable[[str], None]) -> bytes:
|
||||
"""Args:
|
||||
body: {"text", "voice"} as JSON.
|
||||
admit: called with a line before it renders and not for a cached
|
||||
one; it raises to hold the render back.
|
||||
|
||||
Returns:
|
||||
The WAV of the line, from the cache when rendered before.
|
||||
"""
|
||||
gap = self.output_gap()
|
||||
if gap:
|
||||
raise Unavailable(f"speech output is off: {gap}")
|
||||
@@ -194,13 +213,16 @@ class Speech:
|
||||
voice = payload["voice"]
|
||||
if not isinstance(voice, str) or voice not in self.voices:
|
||||
raise ToolError("voice must be one of the installed voices")
|
||||
if voice not in self.handed:
|
||||
raise ToolError("voice must be one the hub hands out to a speaker")
|
||||
line = " ".join(bounded(payload, "text", SPEECH_LIMIT).split())
|
||||
if not SPOKEN_LINE.fullmatch(line):
|
||||
raise ToolError(f"text must be 1 to {SPEECH_LIMIT} printable characters")
|
||||
key = digest(f"{voice}\n{line}")
|
||||
target = self.cache / f"{key}.wav"
|
||||
target = self.cache / f"{WORD_CACHE if line in PROCEDURE_LINES else ''}{key}.wav"
|
||||
with self.speaking:
|
||||
if not target.is_file():
|
||||
admit(line)
|
||||
self.render(voice, line, target)
|
||||
self.trim()
|
||||
os.utime(target)
|
||||
@@ -235,7 +257,8 @@ class Speech:
|
||||
partial.unlink(missing_ok=True)
|
||||
|
||||
def trim(self) -> None:
|
||||
kept = sorted(self.cache.glob("*.wav"), key=lambda path: path.stat().st_mtime, reverse=True)
|
||||
spoken = (path for path in self.cache.glob("*.wav") if not path.name.startswith(WORD_CACHE))
|
||||
kept = sorted(spoken, key=lambda path: path.stat().st_mtime, reverse=True)
|
||||
for path in kept[TTS_KEEP:]:
|
||||
path.unlink(missing_ok=True)
|
||||
|
||||
|
||||
Reference in new issue
Block a user