…ciple II.

TransmitModel::setSbMonitor sent "transmit set mon=" but never updated its
local m_sbMonitor, so transmitModel().sbMonitor() read stale until the radio
echoed sb_monitor (measured non-convergent over a 410 ms window on a
FLEX-8400M). Same defect class as #3712 (setAmCarrierLevel).

Mirror the sibling pattern: write m_sbMonitor optimistically on change and
emit micStateChanged() — the signal the MON button's model->widget sync
(PhoneCwApplet::syncPhoneFromModel, connected to micStateChanged) actually
binds to, matching setMonGainSb. NOT phoneStateChanged() (that drives
syncCwFromModel, which never touches the MON button). No feedback loop: the
sync wraps its body in m_updatingFromModel and the toggled handler early-
returns on that flag, so the optimistic setChecked cannot re-emit the command.

Principle II: the command path stays client->radio; the radio's sb_monitor
status echo (parsed at TransmitModel.cpp:104-106) supersedes the optimistic
value, with no feedback loop. Command/status split per Principle I (FlexLib:
command "mon", status key "sb_monitor", Radio.cs:10615).

Blast radius: risk_score=0.411, 23 high-risk affected (top:
MainWindow::MainWindow, MainWindow::wireRadioModel, RadioModel::
troubleshootingSnapshot). All structural noise from class-level granularity;
the change only adds an existing signal emit already wired and feedback-
guarded, no signature/symbol/dependency change. Test-target link surface
unchanged (no new external symbol or include). Note: cmake unavailable in this
environment, so a full build was not run; the edit uses only pre-declared
members/signals isomorphic to verified sibling setters in the same TU.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>