feat(vela): start mocked response flow after push-to-talk commit

docs/protocol.md

@@ -63,7 +63,7 @@ type ClientEvent =
 - a mocked turn emits deterministic `transcript.final`, `response.text.delta`, `response.completed`, and `session.state` events in protocol-valid order
 - `input_audio.append` updates the ephemeral session record and moves the session to `listening`
 - each accepted `input_audio.append` emits one deterministic `transcript.partial` for the current placeholder turn
-- `input_audio.commit` emits exactly one deterministic `transcript.final`, resets the minimal buffered state, and returns the session to `idle`
+- `input_audio.commit` emits exactly one deterministic `transcript.final` and then starts the same deterministic mocked assistant response stream used by `mocked.turn.trigger`
 - after a completed placeholder input cycle, the same socket can still send `mocked.turn.trigger`
 - `response.cancel` is safe to send even when no mocked turn is active
 - `response.cancel` stops any still-pending mocked turn events for the active turn and resets the minimal session state back to `idle`
@@ -92,7 +92,7 @@ Notes:
 - the UI disables the mic control while disconnected, before `session.ready`, or while a mocked turn is already in flight
 - pressing the mic control sends one placeholder `input_audio.append` chunk and releasing it sends `input_audio.commit`
 - while a placeholder push-to-talk turn is in progress, the UI renders the latest `transcript.partial`
-- after placeholder commit, the UI renders the `transcript.final` and clears the partial-only display
+- after placeholder commit, the UI renders the `transcript.final`, clears the partial-only display, and streams the mocked assistant text from the downstream response events
 - the UI copy explicitly labels the mic button as a control shell and not real microphone capture
 - the UI shows a cancel control and enables it only while a mocked turn is active
 - after cancel returns the gateway to `idle`, the UI clears the active-turn indicator but keeps any transcript or response text that was already rendered
@@ -147,9 +147,9 @@ Notes:
 - no audio, STT, LLM, TTS, or external providers participate in this flow
 - `response.cancel` can stop the mocked turn early, suppress any later mocked response events for that turn, and return the session to `idle`
 
-### Deterministic placeholder push-to-talk transcript sequence
+### Deterministic placeholder push-to-talk transcript and mocked response sequence
 
-For this increment, the existing mic-control shell still sends placeholder `input_audio.append` on press and `input_audio.commit` on release. The gateway now translates that shell flow into deterministic mocked transcript events only:
+For this increment, the existing mic-control shell still sends placeholder `input_audio.append` on press and `input_audio.commit` on release. The gateway now translates that shell flow into deterministic mocked transcript events and then reuses the existing mocked response stream:
 
 ```text
 input_audio.append #1
@@ -161,6 +161,11 @@ input_audio.append #N (N > 1)
 
 input_audio.commit after N appends
 → transcript.final("[mocked final] Placeholder push-to-talk transcript completed from N appended chunk(s).")
+→ session.state(thinking)
+→ session.state(speaking)
+→ response.text.delta("[mocked assistant] ")
+→ response.text.delta("This is a deterministic mocked response from the gateway vertical slice.")
+→ response.completed
 → session.state(idle)
 ```
 
@@ -168,7 +173,8 @@ Safe deterministic edge cases for this mocked placeholder flow:
 
 - commit without any prior append is accepted and emits `transcript.final("[mocked final] Placeholder push-to-talk transcript completed without appended audio.")`
 - repeated appends during one placeholder turn are accepted and each append replaces the latest partial transcript with a chunk-count-based deterministic value
-- placeholder commit does not automatically start assistant thinking, response streaming, or audio playback
+- after the final transcript, placeholder commit follows the same mocked `thinking → speaking → response.text.delta* → response.completed → idle` path as `mocked.turn.trigger`
+- `response.cancel` can interrupt this mocked post-commit response path the same way it interrupts `mocked.turn.trigger`; already-rendered transcript or assistant text is not retracted
 
 ## Contract Scope for This Increment
 
@@ -200,6 +206,7 @@ Current mocked-pipeline behavior:
 
 - during an active mocked turn, `response.cancel` returns the session to `idle` immediately
 - any mocked turn timers that have not fired yet are dropped, so no later `response.text.delta` or `response.completed` events are emitted for the cancelled turn
+- the same cancellation behavior applies when a mocked turn was started by `input_audio.commit`
 - once `idle` is restored, the same WebSocket session can start another mocked turn without reconnecting
 
 More general future-state expectations: