feat(song-info): publish the playable stem list, so stems can preload

The stems plugin could only learn its stem list from the highway's WS `ready`,
which arrives once the highway is already up. So it fetched, decoded, and then
handed every stem's PCM to its audio worklet — copying the WHOLE SONG — with the
player already on screen.

For a 4-minute 6-stem pack that is over half a GIGABYTE of memcpy, in one frame,
on the main thread. Measured on a real load: a 698 ms frame, right as the
song-credits card appeared, with the venue video visibly stopping. That is the
"the video pauses when the author appears" report.

GET /api/song/{f}?stems=1 now returns the same list — [{id, url, default}] plus
full_mix_url — so the plugin can start the whole load at `song:loading`, before
the highway (and the venue) is drawn, where a stalled frame costs nothing.
Nothing about the work changes; only WHEN.

Opt-in via the query param so the library's own metadata calls — the hot path —
pay nothing. Deliberately NOT stored in the metadata cache: that is a
fixed-column table, and widening it would mean a schema migration plus a stale
row for every song already scanned, to cache something that is a plain manifest
read on an already-unpacked pack.

The safety property: REST and the WS must publish the SAME list. If they
disagreed the plugin would preload a graph and then throw it away and rebuild —
strictly worse than not preloading. So both now resolve `default` through one
shared helper (stem_default_on, extracted from load_song), and a test rebuilds
the WS's payload from load_song and requires the REST helper to produce the
identical list, rather than pinning either against a snapshot.

Also pinned: the mixdown is lifted OUT of the stem list (spec 5.3 — `full` is
not a layer; listing it beside the instruments would play the whole song on top
of the stems) while staying reachable as full_mix_url, a single-`full` pack keeps
it as its only playable stem, and an unreadable pack yields an empty list rather
than failing the request. Full suite 2608 passed.

Consumed by feedBack-plugin-stems (preloadSong).

lib/routers/song.py

@@ -829,9 +829,56 @@ def post_song_gap_fill(filename: str, data: dict):
     return {"ok": True, "written": additions, "skipped": skipped}
 
 
+def _playable_stems_payload(song_path, filename: str) -> dict:
+    """The playable stems (id/url/default) + full-mix URL for a sloppak.
+
+    Byte-for-byte the same shape the highway's WS `ready` builds — same
+    partition (the mixdown lifted out), same default resolution, same URL form —
+    because the stems plugin now preloads from THIS and then has to agree with
+    what the WS says a moment later, or it rebuilds the graph for nothing.
+
+    Why it exists: the stems plugin could only learn its stem list from the WS
+    `ready`, which arrives once the highway is up. So it decoded, and then copied
+    the whole song's PCM to its worklet, with the player already on screen — half
+    a gigabyte of memcpy in one frame, ~700 ms, freezing the venue video (#…).
+    Given the list at `song:loading` it can do all of that BEFORE the highway
+    appears, behind the loading overlay where a stall costs nothing.
+
+    Opt-in (`?stems=1`) so the library's own metadata calls — the hot path — pay
+    nothing for it.
+    """
+    from urllib.parse import quote
+
+    try:
+        meta = sloppak_mod.extract_meta(song_path)
+    except Exception:
+        return {"stems": [], "full_mix_url": None}
+
+    q_fn = quote(filename, safe="")
+    stems = [
+        {
+            "id": s["id"],
+            "url": f"/api/sloppak/{q_fn}/file/{quote(s['file'])}",
+            "default": bool(s.get("default", True)),
+        }
+        for s in (meta.get("stems") or [])
+        if s.get("id") and s.get("file")
+    ]
+    full_file = meta.get("full_mix_file")
+    return {
+        "stems": stems,
+        "full_mix_url": f"/api/sloppak/{q_fn}/file/{quote(full_file)}" if full_file else None,
+    }
+
+
 @router.get("/api/song/{filename:path}")
-async def get_song_info(filename: str):
-    """Return song metadata, from cache or by extracting it from the song source."""
+async def get_song_info(filename: str, stems: int = 0):
+    """Return song metadata, from cache or by extracting it from the song source.
+
+    `?stems=1` additionally returns the playable stem list with URLs, so the
+    stems plugin can start fetching/decoding on `song:loading` instead of waiting
+    for the highway's WS `ready` (see _playable_stems_payload).
+    """
     import asyncio
     dlc = _get_dlc_dir()
     if not dlc:
@@ -854,8 +901,21 @@ async def get_song_info(filename: str):
 
     mtime, size = appstate.stat_for_cache(song_path)
     cached = appstate.meta_db.get(cache_key, mtime, size)
+    loop = asyncio.get_event_loop()
+
+    # The stem list is NOT stored in the metadata cache: that is a fixed-column
+    # table, and widening it would mean a migration plus a stale row for every
+    # song already scanned. It is cheap to read on demand (the pack is unpacked
+    # by then, so this is a plain manifest read), and only the opt-in caller pays.
+    async def _with_stems(meta: dict) -> dict:
+        if not stems:
+            return meta
+        extra = await loop.run_in_executor(
+            None, _playable_stems_payload, song_path, filename)
+        return {**meta, **extra}
+
     if cached:
-        return cached
+        return await _with_stems(cached)
 
     # Extract in thread pool
     def _extract():
@@ -863,5 +923,5 @@ async def get_song_info(filename: str):
         appstate.meta_db.put(cache_key, mtime, size, meta)
         return meta
 
-    meta = await asyncio.get_event_loop().run_in_executor(None, _extract)
-    return meta
+    meta = await loop.run_in_executor(None, _extract)
+    return await _with_stems(meta)

lib/sloppak.py

@@ -80,6 +80,20 @@ def find_full_mix(stems: list[dict]) -> dict | None:
     )
 
 
+def stem_default_on(raw) -> bool:
+    """Whether a manifest stem entry plays by default.
+
+    Absent means on. A string is honoured so a hand-written manifest can say
+    `default: off`. Extracted so the WS `ready` payload and the REST song-info
+    payload cannot drift: the stems plugin now preloads from REST and then has
+    to agree with what the WS says a moment later, or it would rebuild the whole
+    graph for nothing.
+    """
+    if isinstance(raw, str):
+        return raw.lower() not in ("off", "false", "0", "no")
+    return bool(raw)
+
+
 def partition_stems(stems: list[dict]) -> tuple[dict | None, list[dict]]:
     """Split stem descriptors into (mixdown, instrument_stems) for PLAYBACK.
 
@@ -1100,12 +1114,11 @@ def load_song(
         sfile = str(s.get("file", ""))
         if not sid or not sfile:
             continue
-        default_val = s.get("default", True)
-        if isinstance(default_val, str):
-            default_on = default_val.lower() not in ("off", "false", "0", "no")
-        else:
-            default_on = bool(default_val)
-        stems.append({"id": sid, "file": sfile, "default": default_on})
+        stems.append({
+            "id": sid,
+            "file": sfile,
+            "default": stem_default_on(s.get("default", True)),
+        })
 
     # The complete mixdown is a stem (spec §5.3), but it is not a *layer*: lift
     # it out so that no consumer of `stems` — the mixer, the library's stem
@@ -1265,7 +1278,15 @@ def extract_meta(path: Path) -> dict:
             isinstance(sid, str) and sid
             and isinstance(sfile, str) and sfile
         ):
-            valid_stems.append({"id": sid, "file": sfile})
+            # `file` and `default` ride along so the REST song-info payload can
+            # publish the same playable-stem list the WS `ready` message does —
+            # the stems plugin needs it BEFORE the highway connects (see
+            # get_song_info). Same helper as load_song, so they cannot disagree.
+            valid_stems.append({
+                "id": sid,
+                "file": sfile,
+                "default": stem_default_on(s.get("default", True)),
+            })
     # Partition exactly as load_song() does, for the same reason the library
     # filter must not lie: `full` is the mixdown, not an instrument (spec §5.3).
     # A separated pack that retains it would otherwise offer the user a "full"
@@ -1292,4 +1313,11 @@ def extract_meta(path: Path) -> dict:
         "stem_count": stem_count,
         # feedBack#129: per-stem filter needs the id list, not just count.
         "stem_ids": stem_ids,
+        # The PLAYABLE stems (id/file/default), partitioned exactly as load_song
+        # does — the mixdown lifted out, never a layer. get_song_info turns these
+        # into URLs so the stems plugin can start fetching and decoding on
+        # `song:loading`, instead of waiting for the highway's WS `ready`.
+        "stems": instrument_stems,
+        # The mixdown, when the pack carries one (spec §5.3). Same reason.
+        "full_mix_file": (_full or {}).get("file") or None,
     }

tests/test_song_info_stems.py

@@ -0,0 +1,131 @@
+"""`/api/song/{f}?stems=1` — the playable stem list, for preloading.
+
+The stems plugin could only learn its stem list from the highway's WS `ready`,
+which arrives once the highway is already up. So it decoded the stems and then
+copied the whole song's PCM to its audio worklet with the player on screen —
+half a gigabyte of memcpy in one frame, ~700 ms, which froze the venue video.
+
+Given the list at `song:loading` it can do all of that BEFORE the highway
+appears, behind the loading overlay where a stall costs nothing.
+
+The safety property these tests exist for: the REST payload must be the SAME
+list the WS builds. If they disagree, the plugin preloads one graph and then
+throws it away and rebuilds another — strictly worse than not preloading. So
+they are pinned against each other, not just against a snapshot.
+"""
+
+import zipfile
+
+import yaml
+
+import sloppak
+
+
+def _pak(tmp_path, stems, full=None, name="song.feedpak"):
+    manifest = {
+        "title": "T", "artist": "A", "duration": 10.0,
+        "arrangements": [],
+        "stems": stems,
+    }
+    if full:
+        manifest["stems"] = stems + [full]
+    p = tmp_path / name
+    with zipfile.ZipFile(p, "w") as z:
+        # Real packs carry manifest.yaml — a JSON manifest is not read at all.
+        z.writestr("manifest.yaml", yaml.safe_dump(manifest))
+    return p
+
+
+def test_extract_meta_carries_file_and_default(tmp_path):
+    p = _pak(tmp_path, [
+        {"id": "guitar", "file": "stems/guitar.ogg"},                 # absent => on
+        {"id": "vocals", "file": "stems/vocals.ogg", "default": False},
+        {"id": "drums", "file": "stems/drums.ogg", "default": "off"},  # string form
+    ])
+    meta = sloppak.extract_meta(p)
+    by_id = {s["id"]: s for s in meta["stems"]}
+    assert by_id["guitar"]["default"] is True, "absent default means ON"
+    assert by_id["vocals"]["default"] is False
+    assert by_id["drums"]["default"] is False, "'off' must be honoured"
+    assert by_id["guitar"]["file"] == "stems/guitar.ogg"
+
+
+def test_the_mixdown_is_lifted_out_of_the_stem_list(tmp_path):
+    # `full` is the mixdown, not a layer (spec 5.3). Listing it beside the
+    # instruments would make the plugin play the whole song ON TOP of the stems.
+    p = _pak(tmp_path,
+             [{"id": "guitar", "file": "stems/guitar.ogg"},
+              {"id": "bass", "file": "stems/bass.ogg"}],
+             full={"id": "full", "file": "stems/full.ogg"})
+    meta = sloppak.extract_meta(p)
+    ids = [s["id"] for s in meta["stems"]]
+    assert ids == ["guitar", "bass"], "the mixdown must not be a layer"
+    assert meta["full_mix_file"] == "stems/full.ogg", "...but it must still be reachable"
+
+
+def test_a_single_full_pack_keeps_full_as_its_only_stem(tmp_path):
+    # A pack whose ONLY stem is `full` is a single-mix pack: there is nothing to
+    # be pristine against, so `full` stays playable and no mixdown is surfaced.
+    p = _pak(tmp_path, [{"id": "full", "file": "stems/full.ogg"}])
+    meta = sloppak.extract_meta(p)
+    assert [s["id"] for s in meta["stems"]] == ["full"]
+    assert meta["full_mix_file"] is None
+
+
+def test_default_resolution_is_shared_with_load_song(tmp_path):
+    # The whole point: REST and the WS must not drift. Both go through
+    # stem_default_on, so pin the helper's contract directly.
+    assert sloppak.stem_default_on(True) is True
+    assert sloppak.stem_default_on(False) is False
+    assert sloppak.stem_default_on("off") is False
+    assert sloppak.stem_default_on("false") is False
+    assert sloppak.stem_default_on("0") is False
+    assert sloppak.stem_default_on("no") is False
+    assert sloppak.stem_default_on("on") is True
+    assert sloppak.stem_default_on(1) is True
+
+
+def test_rest_payload_matches_what_the_ws_would_build(tmp_path):
+    """The safety property, pinned end to end.
+
+    Rebuild the WS's stems_payload from load_song exactly as ws_highway does,
+    and require the REST helper to produce the identical list.
+    """
+    from urllib.parse import quote
+    from routers.song import _playable_stems_payload
+
+    p = _pak(tmp_path,
+             [{"id": "guitar", "file": "stems/guitar.ogg"},
+              {"id": "vocals", "file": "stems/vocals.ogg", "default": "off"}],
+             full={"id": "full", "file": "stems/full.ogg"},
+             name="Iron Maiden - Phantom.feedpak")
+
+    cache = tmp_path / "cache"
+    cache.mkdir()
+    loaded = sloppak.load_song(p.name, tmp_path, cache)
+
+    q_fn = quote(p.name, safe="")
+    ws_stems = [
+        {"id": s["id"], "url": f"/api/sloppak/{q_fn}/file/{quote(s['file'])}",
+         "default": s["default"]}
+        for s in loaded.stems
+    ]
+    ws_full = f"/api/sloppak/{q_fn}/file/{quote(loaded.full_mix)}" if loaded.full_mix else None
+
+    rest = _playable_stems_payload(p, p.name)
+
+    assert rest["stems"] == ws_stems, (
+        "REST and the WS must publish the SAME stem list — a mismatch means the "
+        "plugin preloads a graph and then rebuilds it, which is worse than not "
+        "preloading at all"
+    )
+    assert rest["full_mix_url"] == ws_full
+
+
+def test_a_broken_pack_yields_an_empty_list_not_an_error(tmp_path):
+    # Preloading is an optimisation. A pack we cannot read must fall back to the
+    # normal WS-driven path, never break the song-info request.
+    from routers.song import _playable_stems_payload
+    bad = tmp_path / "bad.feedpak"
+    bad.write_bytes(b"not a zip")
+    assert _playable_stems_payload(bad, "bad.feedpak") == {"stems": [], "full_mix_url": None}