[Fix] Voice doubles and misorders replies to small talk

.changeset/voice-small-talk-stays-with-voice.md

@@ -0,0 +1,5 @@
+---
+"@roomote/web": patch
+---
+
+Voice answers greetings and small talk itself again instead of starting a Fast turn for every utterance, which doubled replies and read out of order; it still never states facts about code, tools, or the product without Fast.

apps/docs/voice.mdx

@@ -37,9 +37,9 @@ and receives only the negotiated session answer; it never receives the API key.
    confirms the call is open; a falling tone marks the end. A **Call started**
    marker appears in the Session.
 3. Talk to Roomote the way you would on a phone call. It acknowledges each
-   utterance in a few words, hands it to the Fast Session, and reports the
-   response out loud when it lands. Every utterance is sent to the Fast Session,
-   where the selected model, tools, context, and safeguards handle the response.
+   request in a few words, hands the work to the Fast Session, and reports the
+   result out loud when it lands. Greetings, thanks, and small talk are
+   answered directly without starting Fast work.
 4. Speak at any time to interrupt. Roomote keeps listening while it speaks,
    and follow-ups go back through the same Fast Session. You can also type in
    the composer during the call.

apps/web/src/app/(sandbox)/sessions/[sessionId]/FastSessionTranscript.tsx

@@ -1123,6 +1123,7 @@ export function FastSessionTranscript({
   const requestInFlightRef = useRef(false);
   const liveVoice = useLiveVoice({
     onUtterance: enqueueVoiceUtterance,
+    onHeardTurn: (text) => recordVoiceTurnRef.current('user', text),
     onSpokenTurn: (text) => {
       if (requestInFlightRef.current) {
         heldSpokenTurnsRef.current.push(text);
@@ -1258,9 +1259,9 @@ export function FastSessionTranscript({
     }
   }, [messages, streamMessages, liveVoiceActive]);
 
-  // The call is transcribed into the Session: Fast turns record what the
-  // person said, this path records what the voice said, and call events mark
-  // where the conversation started and ended.
+  // The call is transcribed into the Session: what the person said when the
+  // voice answered directly, what the voice said, and where the call started
+  // and ended. Delegated requests are recorded by the Fast turn they start.
   const recordVoiceTurn = useCallback(
     (role: 'user' | 'assistant', text: string) => {
       // The finished words stay on screen until their persisted row arrives.