diff --git a/docs/superpowers/specs/2026-07-01-slice-4-barge-in-design.md b/docs/superpowers/specs/2026-07-01-slice-4-barge-in-design.md
new file mode 100644
index 0000000..6f05163
--- /dev/null
+++ b/docs/superpowers/specs/2026-07-01-slice-4-barge-in-design.md
@@ -0,0 +1,613 @@
+# Rutster slice 4 — Barge-in: VAD-driven playout kill on a dedicated media thread
+
+- **Status:** Draft (pending review)
+- **Date:** 2026-07-01
+- **Spearhead step:** 4 of 6 (vision-revision §10 / PORT_PLAN "Phasing")
+- **Origin:** brainstorming session 2026-07-01
+- **Depends on:** [slice 1 — WebRTC media loopback](2026-06-28-slice-1-webrtc-loopback-design.md),
+ [slice 2 — The agent tap](2026-06-28-slice-2-agent-tap-design.md), and slice-3's
+ OpenAI Realtime brain (merged as `c30a452` — `MockRealtimeBrain` + translator + the
+ `speech_started` / `speech_stopped` advisory events). All three must be landed and green.
+- **Related:** [ADR-0002](../../adr/0002-north-star-and-fused-core.md) (fused vertical — the
+ hot-path hop invariant this slice re-affirms), [ADR-0008](../../adr/0008-fob-and-green-zone.md)
+ (FOB/green-zone doctrine — the reflex is a FOB member: hot-path, differentiating),
+ [ARCHITECTURE.md §"Biggest technical risk"](../../ARCHITECTURE.md) (the reflex loop *is*
+ the remaining long pole), [ARCHITECTURE.md §"Media plane"](../../ARCHITECTURE.md)
+ ("Dedicated timing threads for the 20ms loop, **never the shared tokio pool**" — this
+ slice finally lands that mandate).
+
+---
+
+## TL;DR
+
+Stand up spearhead step 4: the **FOB reflex loop**. Slice 3 pre-paved the advisory signals
+(`speech_started` / `speech_stopped` from the brain) and locked the turn-ownership decision
+(OpenAI Realtime server-side VAD disabled; the FOB owns turn-taking). Slice 4 **acts** on
+those advisories: on `speech_started`, the FOB kills playout from the core-authoritative
+buffer; playout resumes when the brain's *first fresh `audio_out` after the barge* arrives,
+proving the brain has yielded and started a new response. No brain round-trip gates the
+kill — the decision lives in the 20 ms media loop.
+
+Slice 4 also **graduates the media loop off the tokio pool**: a single dedicated `std::thread`
+owns all `RtcSession`s exclusively and drives the 20 ms tick via `std::thread::sleep`. This
+honors ARCHITECTURE.md's "never the shared tokio pool" mandate, which slice-1 explicitly
+deferred to "step 4 (barge-in)" (`loop_driver.rs:18-23`). The graduation is load-bearing:
+the reflex is the differentiator and the long pole, and its timing discipline demands a
+thread that doesn't compete with the axum runtime for scheduling.
+
+The **seam slice 1→3 preserved** (`loop_driver.rs` + `rtc_session.rs` byte-identical) holds
+for slice-4 as well: the reflex is a `Reflex
` wrapper decorating the `AudioPipe` trait,
+invisibly to `loop_driver::drive`. Only the binary-side wiring (`session_map.rs` →
+`media_thread.rs`) changes shape; the media crate's hot path stays untouched.
+
+---
+
+## 1. Scope
+
+### 1.1 In scope
+
+- Implementation of spearhead step 4: **barge-in / VAD-driven playout kill**, where "VAD"
+ for the MVP is the brain's `speech_started` / `speech_stopped` advisory (slice-3 pre-paved)
+ — no local DSP energy detector this slice (deferred).
+- A **new `Reflex` wrapper** (`rutster-media/src/reflex.rs`) that decorates the
+ pipe the `RtcSession` holds. The reflex owns the mute state machine, the advisory channel
+ receiver, and the barge-in flush trigger. It is the concrete embodiment of ARCHITECTURE.md's
+ "local real-time reflexes" row for the barge-in case.
+- A **new `barge_in_flush` method on the `AudioPipe` trait** (default impl delegates to
+ `clear_playout_ring`) — the seam object's "kill now" path: clear the playout ring AND drain
+ the brain-bound `rx_audio_out` channel of any frames queued before the barge so the first
+ `audio_out` observed post-barge is provably post-barge. `TapAudioPipe` overrides;
+ `EchoAudioPipe` uses the default.
+- A **new `AdvisoryEvent` enum** (`SpeechStarted { at }`, `SpeechStopped { at }`) flowing
+ over a tokio mpsc from the TapEngine (tokio) to the Reflex (media thread). The engine
+ pushes the events it already decodes from the brain (slice-3 wired these as log+count;
+ slice-4 *forwards* them into the reflex).
+- A **new dedicated media thread** (`rutster/src/media_thread.rs`) replacing the tokio
+ `spawn_poll_task`. One `std::thread::spawn` at binary startup owns
+ `HashMap` exclusively; all access from axum is via a command
+ channel (`AcceptOffer`, `Delete`, `Shutdown`). The 20 ms tick is `std::thread::sleep`.
+- **Rewired `session_map.rs`** (binary): `SessionEntry.rtc: Arc>` →
+ `cmd_tx: mpsc::Sender`. `create_session`, `post_offer`, `close`,
+ `spawn_poll_task` all route through the command channel. The async handlers are cold-path;
+ no cross-thread coordination happens on the 20 ms tick.
+- **`MockRealtimeBrain` extension** (`rutster-brain-realtime/src/mock.rs`): gains the ability
+ to emit `speech_started` / `speech_stopped` on a programmable schedule (e.g. "after N
+ audio_in frames received, send `speech_started`; after M more, send `speech_stopped`").
+- **Barge-in e2e integration test** (extends slice-3's
+ `crates/rutster/tests/realtime_integration.rs` harness): synthetic WebRTC peer →
+ MediaThread → TapEngine → MockRealtimeBrain; mock emits `speech_started`; assert playout
+ goes silent within ≤1 tick (20 ms); mock emits fresh `audio_out`; assert playout resumes.
+- New `ReflexMetrics` (`barge_in_count`, `advisory_dropped`, `frames_suppressed`) mirroring
+ `TapMetrics` shape (atomics, snapshot fn). Threaded through the same `TapConn.metrics`
+ surface where reasonable, or a new side-car.
+- Thorough learner-facing comments on the new std-thread / channel-bridge / wrapper-decorator
+ patterns (slice-1 §7 standard carries over).
+
+### 1.2 Out of scope (with scheduled return)
+
+| Deferred item | Returns in | Why deferred |
+|---|---|---|
+| Local VAD (energy/RMS detector in `on_pcm_frame`) | post-spearhead refinement | Advisory-only MVP per slice-4 brainstorming decision. Local VAD needs threshold tuning + DSP analysis worth its own slice; the `Reflex` wrapper shape is designed so a local-VAD decorator composes as a second wrapper outside (or inside) the advisory one. |
+| Per-session media threads / threadpool shard | later rung | Single thread covers spearhead scale (loopback dev + low-concurrency PSTN via slice-5). The command-channel seam between axum and the thread makes the graduation to a threadpool shard localized. |
+| Trickle ICE | later | Unchanged from slice-1 deferral. |
+| Min-mute floor / inter-word-gap debouncing | post-spearhead | `SpeechStopped` is a no-op for mute; a floor timer on resume would protect against brain-yield races (brain emits fresh `audio_out` before the caller's inter-word gap ends). Defer until observed in practice. |
+| Brain-side `input_audio_buffer.interrupt` / `clear` on barge | slice-5 or brain-side | Whether the brain should clear its own input buffer on `speech_started` is a brain-UX decision, not a FOB one; the FOB only kills *playout* (its half-duplex gate). The advisory already tells the brain what happened; the brain's response is its own concern. |
+| Half-duplex gating beyond playout kill | later rung | Barge-in is the first half-duplex reflex; full HD gating (mixing, jitter buffer interaction, multi-party) arrives with conferencing. |
+| TLS on HTTP / WSS | slice-5 | Unchanged. |
+| Authn / authz / multi-tenancy | slice-6 | Unchanged. |
+| Spend cap / abuse gate | slice-6 | Unchanged. |
+| Browser-based automated e2e (Playwright/Selenium) | post-spearhead | Unchanged. The synthetic-peer harness from slice-2/3 is the test vehicle. |
+
+---
+
+## 2. Architecture delta
+
+### 2.1 The reflex wrapper
+
+`Reflex` is a zero-cost-style decorator around any `AudioPipe`. It sits
+between `RtcSession.pipe` (which `loop_driver::drive` calls via `session.pipe.next_pcm_frame()`)
+and the concrete pipe (`TapAudioPipe` in production, `EchoAudioPipe` in slice-1's unit tests).
+`loop_driver` is oblivious to the wrapper: it still calls `session.pipe.next_pcm_frame()`,
+the dynamic dispatch through `Box` lands in `Reflex::next_pcm_frame`, which
+applies the state machine and delegates to `inner.next_pcm_frame()` per the table in §3.2.
+
+The reflex owns three pieces of state:
+- `advisory_rx: mpsc::Receiver` — drained sync-non-blocking via `try_recv`
+ on the 20 ms tick before delegating to `inner`. Fed by the TapEngine task over tokio mpsc.
+- `muted: bool` — the kill state. `next_pcm_frame` returns `None` while muted, *unless* the
+ inner returns `Some` (the resume condition — the first fresh `audio_out` clears mute).
+- `barge_epoch: u64` — incremented on every `SpeechStarted`. Not strictly required for the
+ advisory-only MVP (the flush + drain makes the resume race-free), but it's the seam for a
+ future local-VAD wrapper that could race the advisory. Documented as forward-compatible.
+
+### 2.2 The dedicated media thread
+
+A single `std::thread::spawn` replaces the tokio `spawn_poll_task`. The thread owns
+`HashMap` **exclusively** — no `Arc>` shared with
+axum. All access from the axum handlers is via a command channel:
+
+```rust
+enum MediaCmd {
+ AcceptOffer { id: ChannelId, sdp: String, reply: oneshot::Sender> },
+ Delete { id: ChannelId, reply: oneshot::Sender<()> },
+ Shutdown { reply: oneshot::Sender<()> },
+}
+```
+
+The thread loop per 10 ms meta-tick:
+1. Drain `cmd_rx` via `try_recv` loop — handle all pending commands before ticking.
+2. For each session in the map: drain the per-session `flush_rx` side-channel (slice-2's
+ existing disconnect-flush signal) BEFORE `run_poll_once`, then call
+ `RtcSession::run_poll_once(now)` (the unchanged `loop_driver::drive`).
+3. After `run_poll_once`, observe `channel.state`:
+ - `Connected && tap.is_none()` → spawn the TapEngine (tokio task via the
+ `tokio::runtime::Handle` captured at thread-start) + wire
+ `Reflex` as the session's pipe. Mirror of slice-2's spawn seam,
+ relocated from `session_map.rs::drive_all_sessions` to here.
+ - `Closed` → remove the entry + drop the session.
+4. `std::thread::sleep(Duration::from_millis(10))` — 10 ms meta-tick. (Stable API:
+ `std::thread::sleep_until` is nightly-only; `sleep(dur)` is the stable path. The 20 ms
+ outbound encode tick is driven inside `loop_driver::drive` (unchanged); the 10 ms
+ meta-tick gives finer resolution so str0m's `Timeout` outputs are honored promptly.)
+
+**The tokio ↔ std-thread bridge:** all channels are tokio mpsc/oneshot (constructable on
+tokio, drainable via `try_recv`/`blocking_recv` from any thread). The `tokio::runtime::Handle`
+captured at `MediaThread::spawn` time is used on the std thread to `handle.spawn(...)` the
+TapEngine when the `Connected` transition fires. No async code runs on the std thread itself
+— only sync channel ops + `RtcSession::run_poll_once`.
+
+**Why a single thread, not per-session:** spearhead scale. One loopback peer at a time in
+dev; even at low PSTN concurrency (slice-5) one thread drives dozens of sessions in 10 ms.
+Per-session threads arrive when the threadpool shard model lands (deferred). The
+command-channel seam between axum and the thread makes that graduation localized.
+
+### 2.3 The hot-path audit (ADR-0002 honored)
+
+ADR-0002's load-bearing rule: *"the control↔media gRPC hop on the per-call hot path is
+removed."* Slice 4 does not re-introduce a hop:
+
+- The reflex's kill decision happens **inside** `Reflex::next_pcm_frame` on the dedicated
+ thread — no channel send, no cross-thread coordination on the 20 ms tick. The advisory
+ arrives via a `try_recv` drain (sync, non-blocking).
+- axum → media-thread is **cold-path only** (SDP accept, DELETE). None of it runs on the
+ 20 ms tick.
+- The brain WS ↔ TapEngine (tokio) path is unchanged from slice-3. The advisory channel
+ is a *third* mpsc alongside the existing `tx_pcm_in`/`rx_audio_out`/`flush_tx` — same
+ pattern, additive.
+
+**The fused vertical stays fused.** ADR-0002 honored.
+
+---
+
+## 3. Component design
+
+### 3.1 `AdvisoryEvent` enum
+
+```rust
+// crates/rutster-media/src/reflex.rs
+
+/// A turn-event advisory from the brain. The brain decodes its own
+/// speech-to-text / VAD results and forwards these; the FOB *owns*
+/// turn-taking and acts on them (slice-3 §4.3 — OpenAI Realtime
+/// server-side VAD is DISABLED; the FOB's reflex is authoritative).
+///
+/// Carried over a tokio mpsc from the TapEngine (tokio task) to the
+/// `Reflex` wrapper (media thread). Drained sync via `try_recv` on the
+/// 20 ms tick — the kill decision lives in the loop, not in a handler.
+#[derive(Debug)]
+pub enum AdvisoryEvent {
+ /// The brain detected caller speech. Trigger barge-in: kill playout.
+ SpeechStarted { at: Instant },
+ /// The brain detected caller speech ended. Observed + counted; does
+ /// NOT toggle mute (the resume condition is "first fresh audio_out
+ /// after the barge", not "speech_stopped" — see §3.2 state table).
+ SpeechStopped { at: Instant },
+}
+```
+
+### 3.2 `Reflex` state machine
+
+| Current state | Event | Action | New state |
+|---|---|---|---|
+| Playing | `SpeechStarted` | `muted=true`; `epoch++`; `inner.barge_in_flush()` (clear ring + drain `rx_audio_out` so stale brain frames queued pre-barge are dropped); `metrics.barge_in_count++` | Muted |
+| Muted | `SpeechStarted` (duplicate/re-barge) | `epoch++`; `barge_in_flush()` again (fresh barge resets the "fresh audio" clock); `barge_in_count++` | Muted |
+| Muted | `SpeechStopped` | increment `advisory_observed_speech_stopped` counter; **no state change** | Muted |
+| Playing | `SpeechStopped` | increment counter; **no state change** | Playing |
+| Muted | inner `next_pcm_frame()` returns `Some(f)` (fresh brain audio arrived post-barge) | `muted=false`; return `Some(f)` | Playing |
+| Muted | inner `next_pcm_frame()` returns `None` | return `None` (silence); `metrics.frames_suppressed++` | Muted |
+
+**Why `SpeechStopped` is a no-op for mute:** per the resume-semantics decision (resume on
+first fresh `audio_out`). The brain's `speech_stopped` is *observed* (counter) but doesn't
+gate — this avoids the inter-word-gap problem (caller pauses, VAD fires stopped, brain
+un-mutes too early, brain's audio overlaps caller's next word). The resume condition is
+"the brain has yielded and started a new response," which is provably signaled by the first
+`audio_out` frame after the barge — not by the caller's silence.
+
+**Why `epoch`:** not strictly needed for advisory-only (MVP), but it's the seam for the
+local-VAD backstop (deferred per §1.2). A future `LocalVadReflex` wrapper racing the
+advisory would need to disambiguate "is this barge a re-barge of the same event or a new
+one" — the epoch is the disambiguator. Forward-compatible.
+
+### 3.3 `AudioPipe` trait extension
+
+```rust
+// crates/rutster-media/src/pcm.rs — additive method on `AudioPipe`
+
+/// Barge-in flush: clear the playout ring AND drain the inbound brain
+/// audio queue of any frames queued before the barge. Called by `Reflex`
+/// on `SpeechStarted`. The drain of `rx_audio_out` is what makes the
+/// resume condition race-free: the first `audio_out` observed post-barge
+/// is provably post-barge (frames queued pre-barge are dropped here).
+///
+/// Default impl delegates to `clear_playout_ring` — sufficient for
+/// pipes without an inbound queue to drain (like `EchoAudioPipe`).
+fn barge_in_flush(&mut self) {
+ self.clear_playout_ring();
+}
+```
+
+`TapAudioPipe` overrides:
+```rust
+// crates/rutster-tap/src/tap_audio_pipe.rs
+
+fn barge_in_flush(&mut self) {
+ // Clear the playout ring (drops buffered brain-proposed frames).
+ self.playout_ring.clear();
+ // Drain rx_audio_out of any frames the engine task queued before
+ // the barge. Without this, a stale frame in the mpsc would un-mute
+ // immediately on the next tick — defeating the "first fresh audio_out"
+ // resume condition. Hot-path: try_recv loop, bounded, no blocking.
+ while self.rx_audio_out.try_recv().is_ok() {
+ self.metrics.barge_drained_inflight.fetch_add(1, Ordering::Relaxed);
+ }
+}
+```
+
+### 3.4 `Reflex
` struct + impl
+
+```rust
+// crates/rutster-media/src/reflex.rs
+
+pub struct Reflex {
+ inner: P,
+ advisory_rx: mpsc::Receiver,
+ muted: bool,
+ barge_epoch: u64,
+ metrics: Arc,
+}
+
+impl Reflex {
+ pub fn new(inner: P, advisory_rx: mpsc::Receiver, metrics: Arc) -> Self {
+ Self { inner, advisory_rx, muted: false, barge_epoch: 0, metrics }
+ }
+
+ /// Drain all pending advisories + apply the state table. Called at
+ /// the top of `next_pcm_frame`. Hot-path: try_recv loop, bounded.
+ fn drain_advisories(&mut self) {
+ while let Ok(ev) = self.advisory_rx.try_recv() {
+ match ev {
+ AdvisoryEvent::SpeechStarted { at } => {
+ self.muted = true;
+ self.barge_epoch = self.barge_epoch.wrapping_add(1);
+ self.inner.barge_in_flush();
+ self.metrics.barge_in_count.fetch_add(1, Ordering::Relaxed);
+ tracing::info!(epoch = self.barge_epoch, ?at, "barge-in");
+ }
+ AdvisoryEvent::SpeechStopped { at: _ } => {
+ self.metrics.advisory_observed_speech_stopped.fetch_add(1, Ordering::Relaxed);
+ // No state change — see §3.2.
+ }
+ }
+ }
+ }
+}
+
+impl AudioPipe for Reflex {
+ fn next_pcm_frame(&mut self) -> Option {
+ self.drain_advisories();
+ if self.muted {
+ // Muted: pull from inner. Some(f) = fresh brain audio arrived
+ // post-barge → un-mute + return. None = silence, stay muted.
+ match self.inner.next_pcm_frame() {
+ Some(f) => {
+ self.muted = false;
+ Some(f)
+ }
+ None => {
+ self.metrics.frames_suppressed.fetch_add(1, Ordering::Relaxed);
+ None
+ }
+ }
+ } else {
+ self.inner.next_pcm_frame()
+ }
+ }
+
+ fn on_pcm_frame(&mut self, frame: PcmFrame) {
+ // Inbound caller audio is NEVER gated by the reflex. The brain
+ // still hears the caller during barge — that's the point (the
+ // brain needs to know the caller interrupted; the FOB only kills
+ // its OWN playout, not the caller's path to the brain).
+ self.inner.on_pcm_frame(frame)
+ }
+
+ fn clear_playout_ring(&mut self) {
+ // The reconnect-flush path (slice-2 §5.3) still works through the
+ // wrapper. If it fires during mute, the ring stays empty and mute
+ // clears on the next post-reconnect audio_out.
+ self.inner.clear_playout_ring()
+ }
+
+ fn barge_in_flush(&mut self) {
+ // Allow outer wrappers (future local-VadReflex) to barge the inner.
+ self.inner.barge_in_flush()
+ }
+}
+```
+
+### 3.5 `ReflexMetrics`
+
+Mirror of `TapMetrics` shape (atomics + snapshot struct):
+
+```rust
+// crates/rutster-media/src/reflex.rs
+
+#[derive(Default)]
+pub struct ReflexMetrics {
+ pub barge_in_count: AtomicU64,
+ pub advisory_dropped: AtomicU64, // advisory channel full (e.g. 16-cap)
+ pub frames_suppressed: AtomicU64, // None returns while muted
+ pub advisory_observed_speech_stopped: AtomicU64,
+}
+
+pub struct ReflexMetricsSnapshot {
+ pub barge_in_count: u64,
+ pub advisory_dropped: u64,
+ pub frames_suppressed: u64,
+ pub advisory_observed_speech_stopped: u64,
+}
+
+// `barge_drained_inflight` lives on `TapMetrics` (in `rutster-tap`), not
+// `ReflexMetrics`, because the drain happens inside `TapAudioPipe::barge_in_flush`,
+// not inside `Reflex`. The path: `Reflex::drain_advisories` calls
+// `inner.barge_in_flush()` which is `TapAudioPipe::barge_in_flush`, which is
+// where the `rx_audio_out` drain + the counter increment happen.
+```
+
+---
+
+## 4. The dedicated media thread
+
+### 4.1 `MediaThread`
+
+```rust
+// crates/rutster/src/media_thread.rs
+
+pub struct MediaThread {
+ cmd_tx: mpsc::Sender,
+ join: Option>,
+}
+
+enum MediaCmd {
+ AcceptOffer { id: ChannelId, sdp: String, reply: oneshot::Sender> },
+ Delete { id: ChannelId, reply: oneshot::Sender<()> },
+ Shutdown { reply: oneshot::Sender<()> },
+}
+```
+
+Spawned at binary startup (`main.rs`), before `axum::serve`. The thread captures a
+`tokio::runtime::Handle` (to spawn TapEngine tasks when `Connected` transitions fire) and
+owns `HashMap` + (per-session, lazily) the TapConn / advisory_rx /
+Reflex wrapper.
+
+### 4.2 Thread loop (per 10 ms meta-tick)
+
+1. `cmd_rx.try_recv()` loop — handle ALL pending commands before ticking. `AcceptOffer`
+ calls `RtcSession::accept_offer(sdp)` and replies via the oneshot. `Delete` fires
+ `close_tx` + bounded-await the engine task (750 ms cap via
+ `tokio::runtime::Handle::block_on(timeout(...))`) — the std thread briefly enters the
+ tokio runtime to await; cold-path, not the 20 ms tick. `Shutdown` drains + replies.
+2. For each `RtcSession` in the map:
+ - Drain per-session `flush_rx` side-channel (slice-2's existing disconnect-flush) BEFORE
+ `run_poll_once`.
+ - Call `RtcSession::run_poll_once(now)` — the unchanged `loop_driver::drive`.
+ - Observe `channel.state`:
+ - `Connected && tap.is_none()` → `handle.spawn(spawn_tap_engine(...))` to bring up the
+ tokio task; construct `Reflex::new(TapAudioPipe::new(...), advisory_rx, metrics)`;
+ call `RtcSession::set_pipe(reflex)`. Mirror of slice-2's spawn seam.
+ - `Closed` → remove the entry (drops the `RtcSession` + its pipe + advisory ends).
+3. `std::thread::sleep(Duration::from_millis(10))` — 10 ms meta-tick.
+
+### 4.3 `session_map.rs` rewire
+
+`SessionEntry` loses `rtc: Arc>`, gains `cmd_tx: mpsc::Sender`
+(cloned per-entry; cheap). `tap_url` stays (the thread reads it when spawning the engine).
+`tap_conn: Option` moves onto the media thread (the thread owns it after spawn).
+
+- `AppState::create_session` → sends a `Register { tap_url, reply }` command to the media
+ thread; the **thread** constructs `RtcSession::new()` (saves a cross-thread move of the
+ struct + keeps all `RtcSession` construction on the thread that owns it). The thread
+ replies with `(id, cmd_tx_for_this_session)`; axum stores `SessionEntry { cmd_tx, tap_url,
+ tap_conn: None }`.
+- `AppState::get(id)` (SDP path) → `cmd_tx.send(AcceptOffer { ... }).await` + `reply.await`.
+ Cold-path; the axum handler is async.
+- `AppState::close(id)` → `cmd_tx.send(Delete { id, reply }).await` + `reply.await`. The
+ reply returns after the TapEngine teardown completes on the thread.
+- `spawn_poll_task` → `spawn_media_thread`: constructs the channels, spawns the std thread,
+ stores `cmd_tx` + `join` in `AppState`. Same idempotent-guard pattern.
+
+### 4.4 TapEngine extension
+
+`spawn_tap_engine` returns a third channel end: `advisory_tx: mpsc::Sender`.
+The pump loop, on receiving `speech_started` / `speech_stopped` from the brain (slice-3
+already decodes these in the tap protocol layer — `protocol_events.rs`), pushes the
+corresponding `AdvisoryEvent` into `advisory_tx`. If the channel is full, drop + count
+(hot-path "drop + observe" policy; an advisory is a hint, not a command). The `Reflex`
+wrapper holds `advisory_rx`.
+
+### 4.5 `MockRealtimeBrain` extension
+
+`rutster-brain-realtime/src/mock.rs` gains a programmable advisory schedule: the test can
+register "after N `audio_in` frames received, send `speech_started`" and "after M more,
+send `speech_stopped`". The mock already asserts `turn_detection: null` on
+`session.update` (slice-3's S4 lock); slice-4 keeps that assertion.
+
+---
+
+## 5. Data flow
+
+### 5.1 Barge-in (the kill)
+
+```
+1. caller speaks into mic → peer RTP → str0m decode → on_pcm_frame → tx_pcm_in → TapClient → audio_in (WS) → brain
+2. brain's VAD fires → brain sends speech_started back over WS (slice-3 already decodes this)
+3. TapEngine pump loop → push AdvisoryEvent::SpeechStarted → advisory_tx (tokio mpsc, 16-cap)
+4. media thread 20 ms tick → Reflex::next_pcm_frame → drain_advisories → SpeechStarted seen
+ → muted=true; epoch++; inner.barge_in_flush() (ring cleared + rx_audio_out drained)
+ → returns None (silence) for this + subsequent ticks while muted
+5. loop_driver::drive pulls None from pipe → encodes Opus silence → peer hears silence
+ (the brain's in-flight audio_out frames are dropped; no overlap with caller's speech)
+```
+
+### 5.2 Resume (the un-mute)
+
+```
+1. brain decides to yield/respond → sends a fresh audio_out frame
+ (provably post-barge: barge_in_flush drained rx_audio_out)
+2. TapClient → audio_out (WS) → TapEngine → tx_audio_out → rx_audio_out → playout ring
+3. media thread 20 ms tick → Reflex::next_pcm_frame → drain_advisories (empty)
+ → muted=true → inner.next_pcm_frame() returns Some(f) (fresh brain audio)
+ → muted=false; return Some(f)
+4. loop_driver encodes + writes → peer hears the brain's new response
+```
+
+### 5.3 Cold-path (axum ↔ media thread)
+
+```
+- POST /v1/sessions → AppState::create_session → MediaCmd::Register → thread constructs RtcSession → reply(id)
+- POST /v1/sessions/{id}/offer → AppState::get + cmd_tx.send(AcceptOffer) → thread.lock(session).accept_offer(sdp) → reply(answer)
+- DELETE /v1/sessions/{id} → AppState::close → cmd_tx.send(Delete) → thread: fire close_tx, bounded-await engine task teardown → reply
+- graceful shutdown → cmd_tx.send(Shutdown) → thread drains + drops → reply → join
+```
+
+---
+
+## 6. Why these decisions
+
+### 6.1 Why advisory-only (no local VAD) for the MVP
+
+- Matches slice-3's S4 turn-ownership posture: OpenAI Realtime's server-side VAD is disabled;
+ the FOB owns turn-taking. The brain already runs VAD (it has to, to do STT); forwarding its
+ result is the cheapest path to a working barge-in.
+- Local VAD (energy/RMS detector in `on_pcm_frame`) is DSP work + threshold tuning — worth
+ its own slice. The `Reflex` wrapper shape is designed so a `LocalVadReflex` decorator
+ composes outside (or inside) the advisory one when it arrives.
+- YAGNI: prove the advisory→reflex→kill path end-to-end first; add the backstop if the
+ brain's VAD latency proves insufficient in practice.
+
+### 6.2 Why resume on first fresh `audio_out` (not `speech_stopped`)
+
+- The "the brain has yielded and started a new response" condition is provably signaled by
+ the first `audio_out` frame after the barge — not by the caller's silence. `speech_stopped`
+ fires between words; resuming on it un-mutes too early (inter-word-gap overlap).
+- The `barge_in_flush` drain of `rx_audio_out` makes the resume race-free: the first
+ `audio_out` observed post-barge is provably post-barge (frames queued pre-barge are dropped
+ in the flush).
+
+### 6.3 Why a single dedicated thread (not per-session)
+
+- Spearhead scale: one loopback peer in dev; even at low PSTN concurrency (slice-5), one
+ thread drives dozens of sessions in 10 ms.
+- The command-channel seam between axum and the thread makes the graduation to a threadpool
+ shard localized — when per-CPU-shard threading arrives, it's a fan-out of the
+ `cmd_rx`/`HashMap` shape, not a redesign.
+- Per-session threads arrive when load demands; the spearhead's "shortest blocking path"
+ rule dislikes spawning work per session that may not need it (pre-ICE-connected sessions
+ would redundantly spin).
+
+### 6.4 Why `Reflex
` as a wrapper (not inline in `TapAudioPipe`)
+
+- Composition: a future `LocalVadReflex
` composes outside the advisory `Reflex
`, the
+ same way `Reflex` composes today. The pattern (decorator over `AudioPipe`) is
+ forward-compatible without restructuring.
+- The seam: `loop_driver.rs` byte-identical (still calls `pipe.next_pcm_frame()`). If the
+ reflex lived inline in `TapAudioPipe`, the binary-side wiring would still change but the
+ `TapAudioPipe` module itself would grow the reflex state — less isolated.
+- YAGNI caveated: the wrapper is the right abstraction for advisory-only because there's
+ exactly one reflex. When local VAD arrives, the wrapper pattern pays off; the spec does
+ not pre-empt that by collapsing the wrapper now.
+
+### 6.5 Why `barge_in_flush` on `AudioPipe` (not just `clear_playout_ring`)
+
+- `clear_playout_ring` (slice-2) clears the *ring*. `barge_in_flush` clears the ring AND
+ drains the *inbound brain queue* (`rx_audio_out`). The distinction matters: on a brain
+ disconnect (slice-2's case), the brain is gone — `rx_audio_out` will drain itself on the
+ next `Disconnected` `try_recv`. On a barge-in, the brain is alive and may have queued
+ frames pre-barge that would un-mute immediately if not drained here. Two different
+ "clear the playout path" semantics, two methods.
+
+---
+
+## 7. Done-criteria
+
+1. `cargo test --all` passes (stable + 1.85, the CI matrix).
+2. `cargo fmt --check` + `cargo clippy -- -D warnings` clean.
+3. `loop_driver.rs` + `rtc_session.rs` **byte-identical** to slice-3 — CI-asserted via
+ `git diff --exit-code main -- crates/rutster-media/src/loop_driver.rs
+ crates/rutster-media/src/rtc_session.rs` (the §8.5 #6 seam gate, restated for slice-4).
+4. Dedicated media thread drives sessions off the tokio pool; `MediaThread` integration test
+ passes (AcceptOffer / Delete / Shutdown).
+5. `Reflex` state-machine unit tests all pass:
+ - `SpeechStarted` → next `next_pcm_frame` returns None even if ring has frames.
+ - `SpeechStarted` then `inner.next_pcm_frame()=Some` → un-mutes, returns the frame.
+ - `SpeechStopped` during Muted → stays Muted.
+ - `SpeechStopped` during Playing → no-op.
+ - Duplicate `SpeechStarted` re-flushes + stays Muted.
+ - Metrics counters (`barge_in_count`, `frames_suppressed`) increment correctly.
+ - `advisory_rx` full → `advisory_dropped` increments, no panic.
+6. `barge_in_flush` unit tests pass (ring + `rx_audio_out` drain).
+7. Barge-in e2e: `speech_started` → playout silent within ≤1 tick (20 ms); fresh `audio_out`
+ → playout resumes. Extends slice-3's `realtime_integration.rs` harness.
+8. S4 turn-ownership lock preserved: `MockRealtimeBrain` still asserts
+ `turn_detection: null` on `session.update` (slice-3's #7, unchanged).
+9. `MockRealtimeBrain` extended to emit `speech_started`/`speech_stopped` on schedule.
+10. `cargo doc --no-deps` renders the new `reflex.rs` + `media_thread.rs` module/item docs
+ cleanly (learner-facing comments present per AGENTS.md code style).
+
+---
+
+## 8. Open decisions
+
+- ~~Trigger source~~ — decided: advisory-only (brain `speech_started`/`speech_stopped`).
+- ~~Resume semantics~~ — decided: first fresh `audio_out` post-barge; `SpeechStopped`
+ observational only.
+- ~~Thread model~~ — decided: single dedicated `std::thread`; per-session/threadpool deferred.
+- **`MockRealtimeBrain` advisory schedule API shape** — landed in §4.5 as a programmable
+ "after N audio_in frames" schedule. Could alternatively be a free-form
+ `Vec<(trigger_frame_count, AdvisoryEvent)>` queue. The plan will pin the concrete API.
+- **Thread shutdown ordering vs TapEngine teardown** — `Delete` command handler fires
+ `close_tx` + bounded-await the engine task (750 ms cap via
+ `tokio::runtime::Handle::block_on(timeout(...))`); the reply oneshot returns after
+ teardown. Cold-path, std thread briefly enters the tokio runtime to await. Documented as
+ an acceptable deviation (not the 20 ms tick).
+
+---
+
+## 9. Cross-references
+
+- [slice-1 spec](2026-06-28-slice-1-webrtc-loopback-design.md) — the media loop + the seam
+ (`AudioSource`/`AudioSink` traits in `rutster-media`); slice-1 §8.5 #6 is the seam gate
+ this slice re-affirms.
+- [slice-2 spec](2026-06-28-slice-2-agent-tap-design.md) — the tap interface, the
+ `TapAudioPipe`, the core-authoritative playout buffer (§4.1), the `flush_tx` side-channel
+ pattern that the `advisory_rx` mirrors.
+- slice-3 (merged `c30a452`) — `MockRealtimeBrain`, the translator, the
+ `speech_started`/`speech_stopped` protocol events, the S4 turn-ownership lock.
+- [ADR-0002](../../adr/0002-north-star-and-fused-core.md) — fused vertical; the hot-path
+ hop invariant this slice re-affirms (§2.3 audit).
+- [ADR-0008](../../adr/0008-fob-and-green-zone.md) — FOB/green-zone doctrine; the reflex is
+ a FOB member (hot-path, security-constitutive for turn-taking, differentiating).
+- [ARCHITECTURE.md](../../ARCHITECTURE.md) — §"Media plane" ("Dedicated timing threads
+ for the 20ms loop, never the shared tokio pool" — this slice lands it); §"Biggest
+ technical risk" (the reflex loop *is* the remaining long pole).
+- [PORT_PLAN.md](../../PORT_PLAN.md) — §Phasing, step 4 = barge-in.