add sessions/0021/SESSION-0021.0-TRANSCRIPT-2026-06-26T08-12--2026-06-26T08-20.md + replace placeholder/variant SESSION-0021.0-TRANSCRIPT-2026-06-26T08-12--INPROGRESS.md

Operator-driven revision of the audio feature: Dev-Mode-style Video/Audio toggles,
white-noise deferred (Audio = off/soundtrack), and fixes for two real-browser bugs
(video-off not blanking GPU-composited layers; no soundtrack on Safari/iOS).
Verified in headless Chromium + WebKit. 288 tests + 3 Playwright E2E pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.gitignore

@@ -17,3 +17,6 @@ simulator/sample_media/**/*.m4a
 # Local-only candidate review galleries (re-buildable; not shipped content).
 simulator/static/review.html
 simulator/static/review_audio.html
+
+# Editor annotation/comment-thread metadata (not project content)
+.threads/

docs/superpowers/specs/2026-06-26-audio-video-separated-controls-design.md

@@ -1,8 +1,18 @@
 # Audio + Video — separated Visual & Audio controls — design
 
-**Status:** proposed → in implementation (plan `docs/superpowers/plans/2026-06-26-audio-video-separated-controls.md`, session 0020)
+**Status:** proposed → built (sessions 0020 build + 0021 revision)
 **Date:** 2026-06-26
-**Session:** 0020 (audio)
+**Session:** 0020 (audio) · 0021 (live-UI revision)
+
+> **v1 build revision (session 0021, operator-driven):** the live **Audio** control
+> ships as a simple **off / soundtrack** toggle (styled like the Dev Mode switch),
+> and **Video** is the matching on/off toggle. **White-noise is deferred** with music
+> (the orthogonal Visual × Audio model and the synthesized-pink-noise machinery
+> remain in the codebase for when it's wanted). Two real-browser bugs were fixed in
+> this revision: video-off now blanks GPU-composited layers (z-index + explicit layer
+> hide), and the soundtrack now plays on Safari/iOS (audio elements unlocked
+> synchronously inside the start gesture). Sections below describe the fuller
+> off/soundtrack/white-noise design; v1 live = off/soundtrack.
 **Extends / reframes:** [`2026-06-26-networked-control-surface-design.md`](./2026-06-26-networked-control-surface-design.md)
 §3 (control inventory) and §5 (server contract) — its bundled **Content** selector
 is split into two orthogonal controls. Everything else in that spec (server-of-truth

docs/superpowers/specs/2026-06-26-networked-control-surface-design.md

@@ -75,7 +75,7 @@ inventory is exactly what the sim exposes today:
 | Control | Sim today | Physical form (later) |
 |---|---|---|
 | **Visual** | toggle (show video on/off) | 2-position switch |
-| **Audio** | 3-way `<select>` (off / soundtrack / white noise; ·music deferred) | rotary selector switch (3 pos) |
+| **Audio** | on/off toggle (on = per-altitude soundtrack; ·white-noise & music deferred) | 2-position switch (rotary selector when more sources land) |
 | **Altitude** | endless circular dial — walks the 5 scales (cosmos→abyss), wraps | rotary encoder (endless, detented) |
 | **Left** (analytical) | slider 0–4 | knob/pot, 5 detents |
 | **Right** (dreamlike) | slider 0–4 | knob/pot, 5 detents |

player/audio.py

@@ -2,17 +2,18 @@
 §4/§6). The single source of truth for: whether the projector shows video, and
 which audio url plays for a given (audio source, current altitude).
 
-Replaces player/content.py's 7-way bundled table. White-noise is a global,
-altitude-independent bed; soundtrack follows the single Altitude dial; off is
-silence. `music` is a reserved, deferred source — not in v1."""
+Replaces player/content.py's 7-way bundled table. Soundtrack follows the single
+Altitude dial; off is silence. `white_noise` and `music` are deferred sources —
+not in v1 (the live control is a simple Audio on/off toggle where on=soundtrack)."""
 
 from __future__ import annotations
 
 from dataclasses import dataclass
 
 VISUAL_POSITIONS = frozenset({"on", "off"})
-# v1 audio sources. "music" is reserved/deferred (no assets) and intentionally absent.
-AUDIO_SOURCES = frozenset({"off", "soundtrack", "white_noise"})
+# v1 audio sources. The live UI is an Audio on/off toggle (on=soundtrack).
+# "white_noise" and "music" are deferred (no live control) and intentionally absent.
+AUDIO_SOURCES = frozenset({"off", "soundtrack"})
 
 
 @dataclass(frozen=True)
@@ -31,24 +32,22 @@ def resolve_visual(position: str) -> bool:
     return position == "on"
 
 
-def resolve_audio_url(source: str, *, scale_audio: str, noise_url: str) -> str | None:
+def resolve_audio_url(source: str, *, scale_audio: str) -> str | None:
     """The audio url for (source, current altitude): soundtrack → the current
-    scale's asset (or None if none authored); white_noise → the global bed; off →
-    None. `scale_audio` is the ring scale's `audio` path (relative to /media/audio/)."""
+    scale's asset (or None if none authored); off → None. `scale_audio` is the ring
+    scale's `audio` path (relative to /media/audio/)."""
     if source not in AUDIO_SOURCES:
         raise ValueError(
             f"unknown audio source {source!r}; expected one of {sorted(AUDIO_SOURCES)}"
         )
     if source == "off":
         return None
-    if source == "white_noise":
-        return noise_url
     # soundtrack — couple to the current altitude's asset
     return f"/media/audio/{scale_audio}" if scale_audio else None
 
 
-def resolve_audio(source: str, *, scale_audio: str, noise_url: str) -> AudioResolution:
+def resolve_audio(source: str, *, scale_audio: str) -> AudioResolution:
     """The full render.audio view: source, resolved url, and whether it follows the
     Altitude dial (true only for soundtrack)."""
-    url = resolve_audio_url(source, scale_audio=scale_audio, noise_url=noise_url)
+    url = resolve_audio_url(source, scale_audio=scale_audio)
     return AudioResolution(source=source, url=url, altitude_coupled=(source == "soundtrack"))

player/controls.py

@@ -2,7 +2,7 @@
 
 This is the serial-contract payload shared with sub-project 4 (firmware). It
 models the full panel from the audio spec §3: a Visual toggle (on/off) + an
-Audio source selector (off/soundtrack/white_noise), the four experience knobs
+Audio source selector (off/soundtrack; white-noise/music deferred), the four experience knobs
 (0..4), and the two intensity levels (volume, brightness). The wire framing
 itself is the separate 3<->4 serial contract; this module is the *decoded* form.
 """

player/state.py

@@ -36,12 +36,12 @@ class TransitionKind:
 class Playback:
     """What should currently be playing. Visual and audio are orthogonal (audio
     spec §2): `video` is whether the projector shows footage, `audio_source` is
-    the independent audio dial (off / soundtrack / white_noise)."""
+    the independent audio dial (off / soundtrack)."""
 
     clip_id: Optional[str]            # None = black walls
     plan: Optional[RenderPlan]        # None when black
     video: bool                       # whether footage is shown (Visual on/off)
-    audio_source: str                 # the Audio dial source (off/soundtrack/white_noise)
+    audio_source: str                 # the Audio dial source (off/soundtrack)
     volume: int
     brightness: int
 

sessions/0020/SESSION-0020.0-TRANSCRIPT-2026-06-26T06-47--2026-06-26T07-58.md

@@ -0,0 +1,109 @@
+# Session 0020.0 — Transcript
+
+> App: human-experience-filter-art
+> Start: 2026-06-26T06-47 (PST)
+> End: 2026-06-26T07-58 (PST)
+> Type: writing-plans (extended into execution — operator approved "then build it" at the plan gate)
+> Posture: careful (execution proceeded under explicit operator approval)
+> Claude-Session: e0cc053a-41fa-416d-a4f5-493f14984e75
+> Anchor: design docs/superpowers/specs/2026-06-26-audio-video-separated-controls-design.md (R2a)
+> Status: FINALIZED
+
+## Launch prompt
+
+> Write the implementation plan for the "Audio + Video — separated Visual & Audio
+> controls" feature, then build it. (Spec:
+> docs/superpowers/specs/2026-06-26-audio-video-separated-controls-design.md.)
+> Split the bundled 7-way Content selector into orthogonal Visual (on/off) ×
+> Audio (off / soundtrack / white noise). Audio follows the single Altitude dial;
+> white noise synthesized (ffmpeg anoisesrc). Reframe the (unbuilt) networked-
+> control-surface spec §3/§5 as a clean pre-implementation edit. Honor the testing
+> tiers; resolve the three §12 flagged decisions.
+
+## Pre-state
+
+- `main` clean at 99a751c. Two stale `--INPROGRESS` placeholders (0015, 0017) from
+  2026-06-24/25 — prior dead sessions, not live; left untouched.
+- The networked-control-surface architecture (SSE / `/remote` / renderer split) was
+  **unbuilt** — the sim is a single fused page (`simulator/static/index.html`) talking
+  to FastAPI via `POST /api/alteration` (knobs) + `POST /api/ring/advance` (altitude).
+- Audio assets (5 sourced ambiences) sat gitignored under `simulator/sample_media/audio/<scale>/`,
+  unreferenced by the manifest, unserved; no `<audio>` element anywhere; video muted.
+
+## Session arc (turn by turn)
+
+1. **Session gate → writing-plans.** Classified the two-part "write the plan, then
+   build it" prompt as the build track's entry; claimed session **0020** (`--type
+   writing-plans`, careful posture). Baseline clean; created branch `session-0020`.
+2. **Scoping.** Read both specs + the audio candidate pool; dispatched an Explore
+   agent to map the current simulator. Key finding: the control-surface architecture
+   is unbuilt, so the audio spec's §6 server contract had no host. **Resolved by the
+   standing simulator-first directive:** build the audio feature into the current
+   single-page sim (ships sound now); reframe the control-surface spec on paper only;
+   do NOT build the SSE/`/remote`/renderer split (it's "v1 hardware," deferred). This
+   build is the "Content step" the audio spec §11 anticipates.
+3. **Plan.** Wrote `docs/superpowers/plans/2026-06-26-audio-video-separated-controls.md`
+   (10 tasks, all testing tiers). Committed + pushed; presented at the careful-posture
+   plan gate. Operator answered **"Approve — build it."** §12 decisions resolved:
+   audio=live (~0.6 s crossfade), noise=pink, autoplay=tap-to-start overlay; asset
+   params −18 LUFS / mp3 / loop mirrors the proven video crossfade recipe.
+4. **Build (TDD, commit per task):**
+   - T1–2: pure ffmpeg audio builders (`tools/pipeline/audio_ops.py`) + runner
+     (`audio_run.py`) + `simulator/build_audio_media.py`; produced the 5 normalized
+     loops + pink-noise bed (gitignored).
+   - T3: `Scale.audio` manifest field + read/emit/serialize + `SCALE_AUDIO`; manifest
+     regenerated (clean diff — only 5 audio lines).
+   - T4–6: pure `player/audio.py` resolver; retired `player/content.py` (+ test);
+     reframed `player/controls.py` + `player/state.py`; `/api/alteration` validates
+     visual+audio and returns `render.video` + server-resolved `render.audio.url` from
+     `altitude_index`. Full Python suite green.
+   - T7–8: client — Content `<select>` → Visual toggle + Audio selector; A/B `<audio>`
+     gain-crossfade layer; tap-to-start gesture. Smoke-tested page + media (200s).
+   - T9: reframed the networked-control-surface spec §3/§4/§5/§6; recorded §12
+     resolutions; ROADMAP note.
+   - T10: Playwright E2E (`[e2e]` extra). Installed Chromium and ran it for real —
+     surfaced + fixed three client issues (see Cut state). **3 E2E pass**, full suite
+     **288 passed, 2 skipped**.
+5. **Verify + ship.** Screenshotted the running app (cosmos plays, soundtrack audibly
+   playing `cosmos/pillars.loop.mp3`, split controls visible, zero JS errors). Merged
+   `session-0020` → `main` (`--no-ff`) and pushed. (`gh` PR create denied — Gitea host;
+   merged locally with branch→merge discipline.)
+
+## Deferred decisions
+
+_No low-confidence autonomous calls. The scope decision (current-sim vs full control
+surface) was approved at the plan gate; the three §12 resolutions were operator-
+delegated by the launch prompt ("resolve the three flagged decisions"); asset params
+(−18 LUFS, mp3, pink) follow the spec's stated direction._
+
+## Cut state
+
+- `main` @ `aa76cd1` (merge of session-0020), clean, synced with origin.
+- **288 tests + 3 Playwright E2E pass; 2 skipped** (opt-in media integration).
+- Three client robustness fixes the E2E drove out (worth remembering):
+  - `fadeVolume` uses `setInterval`, not `requestAnimationFrame` (rAF stalls when the
+    tab is backgrounded → the gain ramp hung in headless).
+  - The start gesture drops per-element "priming": a single page click grants Chrome
+    autoplay document-wide; priming srcless `<audio>` only hung the handler / polluted
+    the paused-state.
+  - `applyAudio` does not `await` `play()` (awaiting a srcless/buffering play can hang).
+- Plan archival: this app has **no content repo** (`CONTENT_REMOTE` empty), so the plan
+  was not archived to a `plans/` collection — it lives in-repo at
+  `docs/superpowers/plans/` and is already on `main`.
+- §9 pipeline: localhost + E2E stage is **green**; there is no PPE/prod infra for this
+  simulator-first art app (deferred with the Pi renderer), so no further ship stage ran.
+
+## Operator plate (what's true now / next)
+
+- The simulator has **sound**: per-altitude soundtracks that follow the Altitude dial +
+  a pink white-noise bed, behind orthogonal **Visual** × **Audio** controls. The unheard
+  audio wants a by-ear review/tune.
+- Deferred (already roadmap-tracked, not re-parked in memory): the **music** layer
+  (reserved Audio position, no assets), the networked-control-surface SSE/`/remote`
+  build, i2v ring transitions, the Pi renderer.
+
+## Next /goal
+
+```
+/goal review/tune the new audio by ear in the sim (per-altitude soundtracks + pink white-noise + the ~0.6s A/B crossfade; tap-to-start), then source/compose the deferred per-altitude music layer (the reserved Audio position), per docs/audio-candidate-pool.md
+```

sessions/0021/SESSION-0021.0-TRANSCRIPT-2026-06-26T08-12--2026-06-26T08-20.md

@@ -0,0 +1,88 @@
+# Session 0021.0 — Transcript
+
+> App: human-experience-filter-art
+> Start: 2026-06-26T08-12 (PST)
+> End: 2026-06-26T08-20 (PST)
+> Type: executing-plans (operator-driven hotfix/revision of session 0020's audio feature)
+> Posture: yolo
+> Claude-Session: e0cc053a-41fa-416d-a4f5-493f14984e75
+> Status: FINALIZED
+
+## Launch prompt
+
+> Show video unchecked doesn't turn off the video. Make "show video" just "Video"
+> and have a toggle like "Dev Mode" has. I can't hear any audio when "soundtrack
+> (follows altitude)" is selected. Let's just have Audio as off/on like Video for
+> now and get rid of white noise.
+
+## Pre-state
+
+- Session 0020 had just merged the audio feature to `main` (Visual×Audio split,
+  per-altitude soundtracks, pink white-noise, A/B crossfade). The operator tested it
+  live and reported three issues.
+
+## Session arc
+
+1. **Diagnosis (the key work).** Both reported bugs were reproduced *only* in the
+   operator's real browser — neither appeared in headless Chromium **or** WebKit
+   (installed `playwright install webkit` to test Safari's engine). Root causes:
+   - **Video-off doesn't blank:** `#vid` (`<video>`) and `#paint` (WebGL `<canvas>`)
+     are GPU-composited layers; the `#black` cover had *auto* z-index, so on a real
+     GPU (Safari/Chrome) the video layer can composite *above* it despite DOM order.
+     Headless software-raster hides this.
+   - **No soundtrack audio:** real Safari/iOS unlocks an `<audio>` element only when
+     `play()` is called *synchronously inside* the user gesture; the 0020 gesture
+     played in an async continuation (after `await fetch`), which Chrome allows but
+     Safari blocks. Headless WebKit relaxes autoplay, so it passed.
+   This is the session's main lesson: **Playwright headless relaxes both GPU
+   compositing and autoplay**, so the 0020 E2E couldn't have caught either — real
+   device / by-eye review is required.
+2. **Fixes (branch `session-0021`):**
+   - **Video** + **Audio** are now Dev-Mode-style on/off toggles (`.dev-switch`),
+     wired on `change`. Audio on → soundtrack; **white-noise deferred** (removed from
+     the live control; `AUDIO_SOURCES={off,soundtrack}`; the pure pink-noise
+     machinery + tests stay for later).
+   - Video-off: `.black` gets `z-index:50` + `translateZ(0)` (own layer) **and** the
+     video layers are set `opacity:0` on video-off (belt-and-suspenders blanking).
+   - Safari audio: the tap-to-start gesture now primes both A/B `<audio>` elements
+     **synchronously in-gesture** (set src, vol 0, `play().then(pause)`), unlocking
+     the later async crossfades.
+   - Server: `player/audio.py` resolver + `controls.py`/`state.py` + `/api/alteration`
+     drop white-noise; `build_audio_media.py` stops emitting the noise bed.
+3. **Verify + ship.** Updated unit/contract/E2E tests; rewrote the 3 E2E for the new
+   toggles (click the visible `.dev-switch-track`; wait for the opacity transition).
+   **288 passed, 2 skipped.** Re-verified in **both Chromium and WebKit**: Audio toggle
+   plays `cosmos/pillars.loop.mp3`, video-off sets vid+paint opacity 0 with `#black`
+   shown, zero JS errors; screenshotted the new toggle UI. Merged `session-0021` →
+   `main` and pushed. (Also untracked a stray `docs/.threads/*.json` editor artifact
+   swept in by `git add -A`, and gitignored `.threads/`.)
+
+## Deferred decisions
+
+_No low-confidence calls. All three changes were explicit operator requests; the
+root-cause fixes (GPU z-index/layer-hide; Safari in-gesture unlock) are the standard
+remedies for these well-known browser behaviors._
+
+## Cut state
+
+- `main` @ `fddb6d6` (merge of session-0021), clean, pushed.
+- **288 tests + 3 Playwright E2E pass** (2 skipped: opt-in media integration).
+- White-noise is deferred, not deleted: `tools/pipeline/audio_ops.white_noise_args` +
+  `audio_run.generate_white_noise` + their tests remain; only the live control + the
+  build-script emission were removed.
+- **Unvalidated by this session:** real-device audio (Safari autoplay) and real-GPU
+  video-off — headless can't exercise either; needs the operator's by-ear/by-eye pass.
+
+## Operator plate
+
+- Video + Audio are simple on/off toggles (Dev-Mode style). Audio on = the current
+  altitude's soundtrack. The two real-browser bugs should now be fixed — but please
+  confirm on a real device (especially iPad/Safari).
+- Deferred: white-noise (easy to re-add as a 3rd Audio position), the per-altitude
+  music layer, the networked-control-surface build, Pi renderer.
+
+## Next /goal
+
+```
+/goal by-ear/by-eye review the audio + Video/Audio toggles on a REAL device (esp. iPad/Safari — headless can't validate Safari autoplay or GPU compositing), then source/compose the deferred per-altitude music layer per docs/audio-candidate-pool.md (or re-enable white-noise as a 3rd Audio position if wanted)
+```

sessions/sessions.json

@@ -55,5 +55,11 @@
   },
   "0019": {
     "title": ""
+  },
+  "0020": {
+    "title": ""
+  },
+  "0021": {
+    "title": ""
   }
 }

simulator/app.py

@@ -39,9 +39,6 @@ STATIC_DIR = Path(__file__).parent / "static"
 MEDIA_DIR = Path(__file__).parent / "sample_media"
 DEFAULT_MANIFEST = MEDIA_DIR / "manifest.json"
 
-# The global white-noise bed (audio spec §5.2): synthesized, altitude-independent.
-NOISE_URL = "/media/audio/noise/pink.mp3"
-
 # Per-process boot token: changes on every server restart so the dev live-reload
 # (below) also fires when Python code changes (which needs a restart), not just
 # when a static asset's mtime changes.
@@ -190,7 +187,7 @@ def create_app(manifest_path: Optional[Path] = None) -> FastAPI:
         scale_audio = ""
         if app.state.ring is not None:
             scale_audio = scale_at(app.state.ring, req.altitude_index).audio
-        audio = resolve_audio(c.audio, scale_audio=scale_audio, noise_url=NOISE_URL)
+        audio = resolve_audio(c.audio, scale_audio=scale_audio)
         return {
             "plan": render_plan_to_dict(plan),
             "render": {

simulator/build_audio_media.py

@@ -1,18 +1,22 @@
-"""Production pass for the 5 per-altitude soundtracks + the white-noise bed
-(audio spec §5.3). The audio analogue of build_pool_manifest.py --media: read the
-sourced ambience clips (re-downloadable per docs/audio-candidate-pool.md), make
-each a seamless loudness-normalized loop, and synthesize the pink-noise bed.
+"""Production pass for the 5 per-altitude soundtracks (audio spec §5.3). The audio
+analogue of build_pool_manifest.py --media: read the sourced ambience clips
+(re-downloadable per docs/audio-candidate-pool.md), and make each a seamless
+loudness-normalized loop.
 
 Media is gitignored; this script is the reproducible record. Outputs land under
-simulator/sample_media/audio/<scale>/<name>.loop.mp3 and audio/noise/pink.mp3,
-served at /media/audio/...  Run:  python simulator/build_audio_media.py
+simulator/sample_media/audio/<scale>/<name>.loop.mp3, served at /media/audio/...
+Run:  python simulator/build_audio_media.py
+
+(White-noise is deferred — the live Audio control is a simple on/off soundtrack
+toggle. `tools.pipeline.audio_run.generate_white_noise` remains for when it's
+wanted, but no noise bed is built here.)
 """
 
 from __future__ import annotations
 
 from pathlib import Path
 
-from tools.pipeline.audio_run import generate_white_noise, process_soundtrack
+from tools.pipeline.audio_run import process_soundtrack
 
 AUDIO = Path(__file__).parent / "sample_media" / "audio"
 
@@ -35,8 +39,6 @@ def main() -> None:
             continue
         dst = process_soundtrack(src, AUDIO / scale / out)
         print(f"  produced {dst.relative_to(AUDIO.parent)}")
-    noise = generate_white_noise(AUDIO / "noise" / "pink.mp3")
-    print(f"  produced {noise.relative_to(AUDIO.parent)}")
 
 
 if __name__ == "__main__":

simulator/static/app.js

@@ -495,14 +495,14 @@ function renderScaleReadout() {
 }
 
 function controls() {
-  // Visual (on/off) and Audio (off/soundtrack/white_noise) are orthogonal dials
-  // (audio spec §2). One bipolar Mood dial (-4 dark .. +4 light) maps onto the
-  // engine's two poles. Calibration gains are pinned to 1.0, so the simulator
-  // sends no calibration — the server uses DEFAULT_CALIBRATION.
+  // Video (on/off) and Audio (on/off) are orthogonal toggles (audio spec §2).
+  // Audio on = the per-altitude soundtrack (white-noise is deferred). One bipolar
+  // Mood dial (-4 dark .. +4 light) maps onto the engine's two poles. Calibration
+  // gains are pinned to 1.0, so the simulator sends no calibration.
   const mood = +$("mood").value;
   return {
     visual: $("visual").checked ? "on" : "off",
-    audio: $("audio").value,
+    audio: $("audio").checked ? "soundtrack" : "off",
     left: +$("left").value, right: +$("right").value,
     dark: mood < 0 ? -mood : 0, light: mood > 0 ? mood : 0,
     volume: 2, brightness: 2,
@@ -520,8 +520,17 @@ async function update() {
   const data = await resp.json();
   readout.textContent = JSON.stringify(data, null, 2);
   applyAudio(data.render.audio);                       // reconcile the audio layer
-  if (!data.render.video.shown) { black.style.opacity = "1"; black.classList.remove("hidden"); return; }
+  if (!data.render.video.shown) {
+    // Blank the screen. Cover with #black AND hide the video layers themselves —
+    // the <video>/<canvas> are GPU-composited and can otherwise show through the
+    // overlay on a real GPU (Safari/Chrome).
+    black.style.opacity = "1"; black.classList.remove("hidden");
+    vid.style.opacity = "0"; paint.style.opacity = "0";
+    return;
+  }
   black.classList.add("hidden");
+  vid.style.opacity = ""; paint.style.opacity = "";    // restore the video layers
+
   try {
     ensureClipMedia();
     applyVideoLook(data.plan.grade.tone, data.plan.dream.intensity);
@@ -944,6 +953,13 @@ async function applyAudio(audio) {
   [audActive, audIdle] = [audIdle, audActive];   // swap roles
 }
 
+// The current altitude's soundtrack url (the ring carries each scale's `audio`),
+// resolved client-side so the start gesture can unlock the elements synchronously.
+function soundtrackUrl() {
+  const s = ring && ring.scales[ringIndex];
+  return s && s.audio ? "/media/audio/" + s.audio : null;
+}
+
 // Browsers block autoplay until a user gesture. The renderer is launched
 // full-screen by the operator; a one-time tap unlocks audio, then it follows
 // state (audio spec §8 — the documented launch step).
@@ -953,11 +969,21 @@ function showStartGesture() {
   ov.id = "start-gesture";
   ov.textContent = "▶ tap to start sound";
   ov.addEventListener("click", () => {
-    // A click anywhere on the page grants Chrome's autoplay permission
-    // document-wide for the session, so later programmatic play() is allowed —
-    // no per-element priming needed (priming srcless elements only pollutes state).
     audioReady = true;
     ov.remove();
+    // Safari unlocks an <audio> element ONLY when play() is called inside the
+    // user gesture itself — not in a later async continuation (Chrome is lenient;
+    // Safari/iOS is not). Prime BOTH A/B elements now, synchronously, at volume 0,
+    // so the async applyAudio() crossfades that follow are allowed to play.
+    const url = soundtrackUrl();
+    if (url) for (const el of [audA, audB]) {
+      try {
+        el.src = mediaUrl(url);
+        el.volume = 0;
+        const pr = el.play();
+        if (pr) pr.then(() => el.pause()).catch(() => {});
+      } catch (_) { /* priming is best-effort */ }
+    }
     audUrl = null;                       // force the next applyAudio to (re)load
     update();                            // re-apply current state, now with audio
   }, { once: true });
@@ -973,9 +999,10 @@ async function main() {
   buildDial();                // draw the altitude knob from the ring's scales
   initDev();                  // wire the Dev Mode toggle + pool picker (reads persisted state)
   renderScaleReadout();
-  for (const id of ["visual", "audio", "left", "right", "mood"]) {
-    $(id).addEventListener("input", debounced);
-  }
+  // Sliders stream on "input"; the Video/Audio toggles fire on "change" (matches
+  // the Dev Mode switch and is the reliable checkbox event across browsers).
+  for (const id of ["left", "right", "mood"]) $(id).addEventListener("input", debounced);
+  for (const id of ["visual", "audio"]) $(id).addEventListener("change", debounced);
   showStartGesture();         // one-time tap unlocks audio (browser autoplay policy, §8)
   // Altitude knob: drag to turn (commit detents on release), scroll to step, tap a label to jump.
   dial.addEventListener("pointerdown", onDialDown);

simulator/static/index.html

@@ -24,17 +24,17 @@
 
     <section class="panel">
       <fieldset>
-        <legend>Visual</legend>
-        <label class="toggle"><input type="checkbox" id="visual" checked /> show video</label>
-      </fieldset>
-
-      <fieldset>
-        <legend>Audio</legend>
-        <select id="audio">
-          <option value="off">off (silence)</option>
-          <option value="soundtrack">soundtrack (follows altitude)</option>
-          <option value="white_noise">white noise</option>
-        </select>
+        <legend>Output</legend>
+        <label class="dev-switch" for="visual">
+          <input type="checkbox" id="visual" checked />
+          <span class="dev-switch-track"><span class="dev-switch-thumb"></span></span>
+          <span class="dev-switch-label">Video</span>
+        </label>
+        <label class="dev-switch" for="audio">
+          <input type="checkbox" id="audio" />
+          <span class="dev-switch-track"><span class="dev-switch-thumb"></span></span>
+          <span class="dev-switch-label">Audio</span>
+        </label>
       </fieldset>
 
       <fieldset>

simulator/static/style.css

@@ -40,8 +40,15 @@ main { display: flex; gap: 1rem; padding: 1rem; flex-wrap: wrap; align-items: fl
 .hud-chip-text.measure { fill: #ffd79a; }
 .hud-conf { fill: #6cf; opacity: 0.8; }
 .hud-status { fill: #8fdcff; font: 2.4px monospace; opacity: 0.9; letter-spacing: 0.15px; }
-.black { position: absolute; inset: 0; background: #000; opacity: 1; transition: opacity 200ms ease; }
+/* z-index + own compositing layer: the <video> and WebGL <canvas> are GPU-
+   composited layers that can paint ABOVE a plain auto-z sibling (Safari/Chrome
+   with a real GPU) despite DOM order — so the black cover needs an explicit
+   stacking order above them to actually blank the screen. */
+.black { position: absolute; inset: 0; background: #000; opacity: 1;
+         z-index: 50; transform: translateZ(0); transition: opacity 200ms ease; }
 .hidden { display: none; }
+/* Stack the two Output toggles (Video / Audio) with a little breathing room. */
+.dev-switch + .dev-switch { margin-top: 0.45rem; }
 .panel { flex: 0 0 280px; display: flex; flex-direction: column; gap: 0.8rem;
          max-height: calc(100vh - 2rem); overflow-y: auto;
          position: sticky; top: 1rem; }

tests/test_e2e_audio.py

@@ -63,36 +63,37 @@ def page(app_url):
         browser.close()
 
 
-def test_white_noise_loads_the_noise_asset(page):
-    page.select_option("#audio", "white_noise")
-    page.wait_for_function(
-        "['audA','audB'].some(id => "
-        "document.getElementById(id).src.includes('/media/audio/noise/pink.mp3'))"
-    )
-
-
-def test_soundtrack_loads_the_current_scale_asset(page):
-    # initial altitude is cosmos (index 0) → soundtrack resolves its scale asset,
-    # not the noise bed (the altitude-coupling itself is covered at the API tier)
-    page.select_option("#audio", "soundtrack")
+def test_audio_toggle_plays_the_current_scale_soundtrack(page):
+    # Audio on (toggle) → the current altitude's soundtrack (cosmos at index 0) plays
+    page.click("label[for='audio'] .dev-switch-track")
     page.wait_for_function(
         "['audA','audB'].some(id => {"
-        "  const s = document.getElementById(id).src;"
-        "  return /\\/media\\/audio\\/.+\\.mp3/.test(s) && !s.includes('noise');"
+        "  const a = document.getElementById(id);"
+        "  return /\\/media\\/audio\\/.+\\.mp3/.test(a.src) && !a.paused;"
         "})"
     )
 
 
-def test_visual_off_keeps_audio_and_fades_video(page):
-    page.select_option("#audio", "white_noise")
+def test_video_toggle_off_blanks_the_screen_and_hides_layers(page):
+    page.click("label[for='visual'] .dev-switch-track")
+    page.wait_for_selector("#black:not(.hidden)")        # black cover shown
+    # the video layers themselves are hidden too (GPU-composite-proof blanking);
+    # wait for the opacity transition to settle to 0
     page.wait_for_function(
-        "['audA','audB'].some(id => "
-        "document.getElementById(id).src.includes('/media/audio/noise/pink.mp3'))"
+        "['vid','paint'].every(id => getComputedStyle(document.getElementById(id)).opacity === '0')"
     )
-    page.uncheck("#visual")
-    page.wait_for_selector("#black:not(.hidden)")       # video faded to black
+
+
+def test_audio_survives_video_off(page):
+    page.click("label[for='audio'] .dev-switch-track")
+    page.wait_for_function(
+        "['audA','audB'].some(id => !document.getElementById(id).paused "
+        "&& document.getElementById(id).src)"
+    )
+    page.click("label[for='visual'] .dev-switch-track")
+    page.wait_for_selector("#black:not(.hidden)")
     playing = page.evaluate(
         "['audA','audB'].some(id => "
         "{const a = document.getElementById(id); return !a.paused && !!a.src;})"
     )
-    assert playing is True                               # audio survives the video fade
+    assert playing is True                               # audio keeps playing with video off

tests/test_player_audio.py

@@ -10,9 +10,6 @@ from player.audio import (
     resolve_visual,
 )
 
-NOISE = "/media/audio/noise/pink.mp3"
-
-
 def test_visual_on_off():
     assert resolve_visual("on") is True
     assert resolve_visual("off") is False
@@ -27,37 +24,36 @@ def test_visual_positions_are_on_off():
     assert VISUAL_POSITIONS == frozenset({"on", "off"})
 
 
+def test_audio_sources_are_off_and_soundtrack():
+    assert AUDIO_SOURCES == frozenset({"off", "soundtrack"})
+
+
 def test_soundtrack_resolves_to_the_current_scales_asset():
-    url = resolve_audio_url("soundtrack", scale_audio="coast/waves.loop.mp3", noise_url=NOISE)
+    url = resolve_audio_url("soundtrack", scale_audio="coast/waves.loop.mp3")
     assert url == "/media/audio/coast/waves.loop.mp3"
 
 
-def test_white_noise_resolves_to_the_global_bed_independent_of_altitude():
-    url = resolve_audio_url("white_noise", scale_audio="coast/waves.loop.mp3", noise_url=NOISE)
-    assert url == NOISE
-
-
 def test_off_resolves_to_silence():
-    assert resolve_audio_url("off", scale_audio="coast/waves.loop.mp3", noise_url=NOISE) is None
+    assert resolve_audio_url("off", scale_audio="coast/waves.loop.mp3") is None
 
 
 def test_soundtrack_with_no_scale_asset_is_silent():
-    assert resolve_audio_url("soundtrack", scale_audio="", noise_url=NOISE) is None
+    assert resolve_audio_url("soundtrack", scale_audio="") is None
 
 
 def test_resolve_audio_marks_only_soundtrack_altitude_coupled():
-    r = resolve_audio("soundtrack", scale_audio="reef/soundscape.loop.mp3", noise_url=NOISE)
+    r = resolve_audio("soundtrack", scale_audio="reef/soundscape.loop.mp3")
     assert isinstance(r, AudioResolution)
     assert r.source == "soundtrack" and r.altitude_coupled is True
     assert r.url == "/media/audio/reef/soundscape.loop.mp3"
-    assert resolve_audio("white_noise", scale_audio="x/y.mp3", noise_url=NOISE).altitude_coupled is False
-    assert resolve_audio("off", scale_audio="x/y.mp3", noise_url=NOISE).altitude_coupled is False
+    assert resolve_audio("off", scale_audio="x/y.mp3").altitude_coupled is False
 
 
 def test_resolve_audio_url_rejects_unknown_source():
     with pytest.raises(ValueError):
-        resolve_audio_url("podcast", scale_audio="", noise_url=NOISE)
+        resolve_audio_url("white_noise", scale_audio="")   # deferred, not a v1 source
 
 
-def test_music_is_not_a_v1_source():
+def test_music_and_white_noise_are_not_v1_sources():
     assert "music" not in AUDIO_SOURCES
+    assert "white_noise" not in AUDIO_SOURCES

tests/test_player_controls.py

@@ -11,7 +11,7 @@ from player.controls import (
 
 def test_visual_and_audio_enums_are_the_v1_positions():
     assert VISUAL_POSITIONS == frozenset({"on", "off"})
-    assert AUDIO_SOURCES == frozenset({"off", "soundtrack", "white_noise"})
+    assert AUDIO_SOURCES == frozenset({"off", "soundtrack"})
 
 
 def test_valid_controls_pass_validation():
@@ -47,10 +47,10 @@ def test_out_of_range_or_non_int_knob_rejected(field, bad):
 
 def test_parse_controls_from_mapping():
     c = parse_controls(
-        {"visual": "on", "audio": "white_noise", "left": 1, "right": 2, "dark": 3,
+        {"visual": "on", "audio": "soundtrack", "left": 1, "right": 2, "dark": 3,
          "light": 0, "volume": 2, "brightness": 1}
     )
-    assert c == Controls("on", "white_noise", 1, 2, 3, 0, 2, 1)
+    assert c == Controls("on", "soundtrack", 1, 2, 3, 0, 2, 1)
 
 
 def test_parse_controls_rejects_unknown_keys():

tests/test_player_state.py

@@ -38,11 +38,11 @@ def test_visual_off_from_video_fades_to_black():
 
 
 def test_audio_survives_visual_off():
-    # white noise + black is now reachable (the gap the bundled dial omitted)
+    # soundtrack + black is reachable (a gap the bundled dial omitted)
     p = Player(LIB)
-    t = p.update(_controls(visual="off", audio="white_noise"))
+    t = p.update(_controls(visual="off", audio="soundtrack"))
     assert t.playback.video is False
-    assert t.playback.audio_source == "white_noise"
+    assert t.playback.audio_source == "soundtrack"
 
 
 def test_no_change_yields_none_transition():
@@ -90,7 +90,7 @@ def test_volume_only_change_is_a_live_update():
 
 def test_audio_source_change_while_black_is_a_live_update():
     p = Player(LIB)
-    p.update(_controls(visual="off", audio="white_noise"))
+    p.update(_controls(visual="off", audio="off"))
     t = p.update(_controls(visual="off", audio="soundtrack"))
     assert t.kind == TransitionKind.LIVE_UPDATE
     assert t.playback.audio_source == "soundtrack"

tests/test_simulator_api.py

@@ -56,13 +56,11 @@ def test_alteration_visual_off_hides_video(client):
     assert body["render"]["video"]["shown"] is False
 
 
-def test_alteration_white_noise_is_altitude_independent(ring_client):
-    for idx in (0, 1, 2):
-        body = ring_client.post("/api/alteration", json={
-            "controls": _controls(audio="white_noise"), "altitude_index": idx,
-        }).json()
-        assert body["render"]["audio"]["url"] == "/media/audio/noise/pink.mp3"
-        assert body["render"]["audio"]["altitude_coupled"] is False
+def test_alteration_off_is_silent(ring_client):
+    body = ring_client.post("/api/alteration", json={
+        "controls": _controls(audio="off"), "altitude_index": 0,
+    }).json()
+    assert body["render"]["audio"] == {"source": "off", "url": None, "altitude_coupled": False}
 
 
 def test_alteration_soundtrack_couples_to_the_given_altitude(ring_client):