Fix missed quiet "yes" after phone confirmation: more sensitive VAD

After the phone confirmation a caller's "yes" wasn't picked up (silence) until
they repeated it louder. Logs: line was live and the half-duplex gate had
reopened, but VAD never fired for ~14s — the quick/quiet "yes" was below
threshold (min_volume 0.3, start_secs 0.2).

Now that HalfDuplexGate gates out the agent's echo while it speaks, VAD can be
sensitive without echo false-triggers (it only listens hard on the caller's
turn). Lowered min_volume 0.3->0.15, start_secs 0.2->0.1, and trimmed the echo
tail 0.5->0.25 so an answer right after the agent stops isn't dropped.

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

.env.example

@@ -62,4 +62,9 @@ HANGUP_DELAY_SECS=4.0
 # Half-duplex: ignore caller audio while the agent speaks (+ tail) so its own echo on the
 # phone line can't trigger a false barge-in that cancels its reply. false = allow barge-in.
 HALF_DUPLEX=true
-ECHO_TAIL_SECS=0.5
+ECHO_TAIL_SECS=0.25
+# VAD kept sensitive (half-duplex gates echo, so this only affects the caller's turn).
+VAD_CONFIDENCE=0.5
+VAD_MIN_VOLUME=0.15
+VAD_START_SECS=0.1
+VAD_STOP_SECS=0.5

CLAUDE.md

@@ -52,9 +52,11 @@ info-only calls (no booking keyword) are never asked for a number.
 `PIPELINE_SAMPLE_RATE = 16000`, `WIRE_SAMPLE_RATE = 8000` are already set correctly.
 No custom audio module needed.
 
-**VAD tuned for telephony** — `confidence=0.5`, `min_volume=0.3` already loosened from
-desktop defaults. These settings directly address the repeat-yourself problem on the
-VAD side.
+**VAD tuned for telephony** — `confidence=0.5`, `min_volume=0.15`, `start_secs=0.1` — kept
+sensitive so a quick/quiet "yes" isn't missed (a caller had to repeat it after the phone
+confirmation). This is safe **because `HalfDuplexGate` gates out the agent's echo while it
+speaks**, so sensitive VAD only listens hard during the caller's own turn and doesn't cause
+echo false-triggers. Addresses the repeat-yourself / missed-short-answer problem.
 
 **Capacity gating** — `MAX_CONCURRENT_CALLS=2` with atomic slot reservation in
 `server.py` prevents GPU thrashing. Keep it.

bot.py

@@ -98,15 +98,18 @@ PIPELINE_SAMPLE_RATE = 16000     # internal rate Whisper/VAD actually need
 
 # VAD tuning. Defaults (confidence 0.7 / min_volume 0.6) are desktop-mic values that can
 # miss short/quiet 8 kHz telephony utterances like "yes" — loosen them for the phone.
+# VAD is kept sensitive so a quick/quiet "yes" isn't missed (a caller had to repeat it). This
+# is safe because HalfDuplexGate gates out the agent's echo while it speaks, so sensitive VAD
+# doesn't cause echo false-triggers — it only listens hard during the caller's own turn.
 VAD_CONFIDENCE = float(os.environ.get("VAD_CONFIDENCE", "0.5"))
-VAD_MIN_VOLUME = float(os.environ.get("VAD_MIN_VOLUME", "0.3"))
-VAD_START_SECS = float(os.environ.get("VAD_START_SECS", "0.2"))
+VAD_MIN_VOLUME = float(os.environ.get("VAD_MIN_VOLUME", "0.15"))
+VAD_START_SECS = float(os.environ.get("VAD_START_SECS", "0.1"))
 VAD_STOP_SECS = float(os.environ.get("VAD_STOP_SECS", "0.5"))
 # Half-duplex: ignore inbound audio while the agent is speaking (+ this tail in seconds)
 # so the agent's own voice echoing back the phone line can't trigger a false barge-in that
 # cancels its reply (= caller hears silence). Set HALF_DUPLEX=false to allow barge-in.
 HALF_DUPLEX = os.environ.get("HALF_DUPLEX", "true").lower() not in ("false", "0", "no")
-ECHO_TAIL_SECS = float(os.environ.get("ECHO_TAIL_SECS", "0.5"))
+ECHO_TAIL_SECS = float(os.environ.get("ECHO_TAIL_SECS", "0.25"))
 
 # Agent persona name — purely for warmth; change/remove freely.
 AGENT_NAME = os.environ.get("AGENT_NAME", "Sofia")