diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3f37b5d..f8c0555 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,7 +21,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   A key that must ship ahead of the spec uses the reserved `x-` prefix (always allowed) or is recorded in
   `feedpak-spec-exceptions.yml` with a tracking issue — and the gate fails if such an exception goes stale,
   so the allowlist can't become somewhere drift hides. `original_audio` is seeded there against #933 so the
-  gate lands green and starts blocking the *next* instance immediately. Docs: [docs/feedpak-spec-gate.md](docs/feedpak-spec-gate.md).
+  gate lands green and starts blocking the *next* instance immediately; the gate takes no position on how
+  #933 resolves (the expected outcome is removing the key, since the spec already carries the mixdown as a
+  stem — not adopting it). Docs: [docs/feedpak-spec-gate.md](docs/feedpak-spec-gate.md).
 
 ### Removed
 - **The classic v2 UI shell is gone — v3 is the only UI (R3a).** `static/index.html`, the
diff --git a/docs/feedpak-spec-gate.md b/docs/feedpak-spec-gate.md
index ecbef26..4285d57 100644
--- a/docs/feedpak-spec-gate.md
+++ b/docs/feedpak-spec-gate.md
@@ -23,6 +23,13 @@ The moment core reads a manifest key the spec doesn't define, that promise break
 The rule this gate enforces: **any manifest key core reads must be in the spec before core ships code that
 depends on it.** Spec first, implementation second.
 
+Note that "get it into the spec" is not automatically the right fix for an existing violation — for
+`original_audio` it isn't. The spec already carries the pre-separation mixdown as a stem
+(`{id: full, file: stems/full.ogg}`), so that key added a *second, redundant* location for audio to a format
+that already had one, and the resolution is to remove it rather than bless it. The gate takes no position on
+which way a violation resolves; it only insists that one of the two happens deliberately, in the open,
+before the code merges.
+
 ## What it checks
 
 We can't mechanically prove core *interprets* a key the way the spec means. We can prove three surface
diff --git a/feedpak-spec-exceptions.yml b/feedpak-spec-exceptions.yml
index 2f47610..b0ef1a2 100644
--- a/feedpak-spec-exceptions.yml
+++ b/feedpak-spec-exceptions.yml
@@ -25,6 +25,13 @@ exceptions:
       Added by #583 (the full mix played while every stem fader sits at unity,
       since demucs recombination is lossy). Core, lib/enrichment.py, and the
       stems plugin all depend on it, but it was never added to the spec — the
-      drift this gate exists to prevent. Seeded here so the gate lands green and
-      starts blocking the *next* instance immediately; remove once the spec
-      adopts the key.
+      drift this gate exists to prevent.
+
+      The expected resolution is REMOVAL, not adoption: the spec already carries
+      the mixdown as a stem ({id: full, file: stems/full.ogg}), so this key added
+      a second, redundant location for audio to a format that already had one.
+      See #933.
+
+      Seeded here so the gate lands green and starts blocking the *next* instance
+      immediately, rather than blocking on #933. The entry goes away when core
+      stops reading the key.