fix(01-07): fold an empty recording into the duration floor

A push too short to produce a single audio callback was reported as a distinct
'no-audio' condition. It is a zero-length recording, so 'duration-floor' is both true
and actionable; 'no-audio' now means only stop() without a matching start(). Also
records why the standalone suite drives capture with browser audio processing off.

avatar/mic.js

@@ -40,6 +40,7 @@ export const GATE = {
 
 /** Reject reasons. Tests assert on these exact strings, so they are exported data. */
 export const REJECT = {
+  /** stop() without a matching start(), or ASR returned nothing at all. */
   NO_AUDIO: 'no-audio',
   DURATION: 'duration-floor',
   RMS: 'rms-floor',
@@ -141,8 +142,10 @@ export function analyse(samples, sampleRate) {
 export function gate(samples, sampleRate) {
   const stats = analyse(samples, sampleRate);
   let reason = null;
-  if (!samples || samples.length === 0) reason = REJECT.NO_AUDIO;
-  else if (stats.durationMs < GATE.MIN_DURATION_MS) reason = REJECT.DURATION;
+  // An empty buffer is not a separate condition, it is a zero-length recording, and
+  // saying "duration-floor" for a push too short to produce a single audio callback is
+  // both true and more useful than a distinct empty-buffer reason nobody can action.
+  if (stats.durationMs < GATE.MIN_DURATION_MS) reason = REJECT.DURATION;
   else if (stats.rms < GATE.MIN_RMS) reason = REJECT.RMS;
   else if (!(stats.modulation >= GATE.MIN_MODULATION)) reason = REJECT.MODULATION;
   return { ok: reason === null, reason, ...stats };
@@ -185,7 +188,16 @@ async function resampleTo(samples, fromRate, toRate) {
  * @param {Function} [opts.emit]        the facade event bus
  * @param {Function} [opts.onListening] called with true/false as capture really starts/stops
  * @param {Function} [opts.isBusy]      returns true while the avatar is thinking or speaking
- * @param {boolean}  [opts.processing]  browser audio processing; see below
+ * @param {boolean}  [opts.processing]  echo cancellation / noise suppression / AGC
+ *
+ * A note on `processing`, which the standalone ASR suite turns OFF deliberately.
+ * Chrome's WebRTC audio processing is very good at steady broadband noise: measured on
+ * this project's own cafe fixture it drops RMS from 0.0577 to 0.0055, so the clip is
+ * rejected by the RMS floor before the modulation condition is ever consulted. That is a
+ * fine outcome in production and a terrible one in a test, because it would leave the
+ * third gate condition unexercised while looking green. The suite therefore verifies the
+ * gate in its PESSIMISTIC configuration - raw microphone, no browser help - which is what
+ * a browser without WebRTC processing actually hands us. Production keeps it on.
  */
 export function createMic({
   emit = () => {},