fix(fish-s2): reference_id was a silent no-op — populate per-voice dirs + guard the regression

reference_id=<name> resolves against the DIRECTORY references/<name>/
(audio + same-basename .lab), not a flat references/<name>.wav. Voices
were staged flat with the per-name dirs left empty, so every
reference_id resolved to nothing and Fish fell back to its default
speaker — every dropdown voice produced byte-identical audio (proven:
Abigail == Imogen == no-ref, same text+seed). This was the real "no
accent" root cause, independent of the asset-engine "undefined" select
bug.

Server fix (applied to irv-ml1): populated references/<name>/<name>.wav
+ <name>.lab for all 32 voices; re-test confirms Imogen/Eleanor/
Beatrice/Abigail/no-ref now all distinct.

Durable hardening + record correction:
- playbook: normalize-layout step (flat <name>.wav -> nested dir, cp -u
  idempotent, when-gated on count mismatch) + an A/B verify gate that
  hard-fails the deploy if two reference_ids yield identical output.
- services.yaml: correct the reference_id resolution doc (dir + .lab,
  not flat wav).
- README + persistent-memory: correct the "reference_id-by-name is THE
  working path, verified" claim — it was a no-op until this fix; the
  prior ECAPA 0.79 result came through the inline base64 path.

docs/asset-engine/services.yaml

@@ -749,10 +749,15 @@ services:
           Eleanor (p228), Beatrice (p229) — consenting VCTK volunteers (CC BY
           4.0), NOT modeled on or representing any public figure. Other female:
           Abigail, Alice, Cora, Elena, Emily, Gianna, Jade, Layla, Olivia,
-          glados. Resolves to <name>.wav + optional <name>.txt transcript;
+          glados. Resolves against the DIRECTORY references/<name>/ (audio +
-          blank = model default/random speaker. To add: drop a clean 5–15s WAV
+          a same-basename <name>.lab transcript inside it) — NOT a flat
-          into the references dir + add the name here. (No /voices API → static
+          references/<name>.wav, which fish-speech ignores (empty/flat-only
-          list; a list-endpoint is the durable fix — see notes.)
+          dirs silently collapse every voice to the model default; root-caused
+          + fixed 2026-06-01). Blank = model default/random speaker. To add:
+          create references/<name>/ with <name>.wav (clean 5–15s) + <name>.lab
+          (transcript) and add the name here; the deploy playbook's normalize
+          step also mirrors any flat <name>.wav into this layout. (No /voices
+          API → static list; a list-endpoint is the durable fix — see notes.)
       - name: references
         type: json
         label: Custom clone (inline base64)

persistent-memory.md

@@ -118,16 +118,30 @@ _As of 2026-06-01:_
   `01KT2K2SY9N7AY69R9V0B4RXSW` → asset-engine-dev). **Workaround until fixed:
   click the dropdown (fires change) or hit the API directly.** My half
   (`blendable: false` catalog flag) is queued — see Recent decisions.
-- **Fish cloning RESOLVED — it clones competently; "not British" was the
+- **Fish "not British" had TWO independent root causes — BOTH now fixed.**
-  undefined bug.** ECAPA-TDNN re-test (2026-06-01): an Imogen-referenced Fish
+  The ECAPA-TDNN re-test (2026-06-01) showed Fish's cloning *engine* works: an
-  clone scores **~0.79 cosine vs the real `Imogen.wav`** (firmly same-speaker)
+  Imogen reference scores **~0.79 cosine vs real `Imogen.wav`** vs **~0.10 vs
-  and only **~0.10 vs Fish's no-reference default voice**. So Fish faithfully
+  the no-reference default** — but that test fed the reference via the inline
-  clones Imogen WHEN it receives the reference. The operator's "Imogen doesn't
+  base64 `references` path, which masked the real defect. **`reference_id`-by-
-  sound British at all" was the `"undefined"` select bug feeding Fish its
+  name (the path the catalog + form actually use) was silently a NO-OP.** Proof
-  DEFAULT voice (≈ a different speaker), NOT a Fish cloning failure. Earlier
+  (2026-06-01): `reference_id=Abigail`, `=Imogen`, and no-reference all returned
-  resemblyzer-based "weak cloner" verdict RETRACTED. No Fish-side fix needed —
+  **byte-identical** audio (md5 `40b6ac73…`, same text+seed) → reference_id was
-  the blocker is entirely the undefined bug (asset-engine-dev). Future voice
+  being ignored entirely, so every dropdown voice collapsed to Fish's default
-  clones operator-handled (pitch-shift deepening abandoned).
+  speaker. Cause: fish-speech resolves `reference_id=<name>` against the
+  **directory** `references/<name>/` (audio + same-basename `.lab`), but the
+  voices were staged as **flat** `references/<name>.wav` + `.txt` with the
+  per-name dirs left **empty** → nothing resolved. **FIX (2026-06-01):**
+  populated `references/<name>/<name>.wav` + `<name>.lab` for all 32 voices;
+  re-test → Imogen/Eleanor/Beatrice/Abigail/no-ref all 5 **distinct**.
+  reference_id now works; British accents come through. Hardened: the
+  deploy playbook gained a normalize-layout step + an A/B smoke gate
+  (`reference_id` MUST change output) so the empty-dir regression can't ship
+  silently. So the "not British" saga was (A) the `"undefined"` select bug
+  (asset-engine, still belt-and-suspenders) AND (B) this reference_id no-op
+  (server-side, FIXED) — B alone would have kept every voice identical even
+  with A fixed. Earlier "reference_id-by-name is THE working path, verified"
+  claim RETRACTED. Pitch-shift deepening abandoned; future clones operator-
+  handled.
 - **On-host consented voice library** — ~992 real-person clips cached in the
   kyutai tts-voices repo (`/worktank/kyutai-tts/.../snapshots/.../`): VCTK
   (CC BY 4.0, accent-tagged speaker IDs), Unmute voice-donations (CC0), EARS +
@@ -182,8 +196,11 @@ _As of 2026-06-01:_
 - `[2026-06-01]` **Fish-S2 catalog v1→v6** (`f3c260e`..`38d9e3b`) — was a
   blank 2-field form; now exposes the full fish-speech ServeTTSRequest surface
   + a 32-voice `reference_id` "Voice" dropdown (STATIC list — Fish has no
-  /voices API). `reference_id`-by-name is the WORKING clone path; the
+  /voices API). `reference_id`-by-name works ONLY when each voice is staged as
-  path-form `references` shape 500s (see Tried and abandoned). Corrected vram
+  a `references/<name>/` dir with `<name>.wav` + `<name>.lab` — was silently a
+  no-op until that layout fix on 2026-06-01 (see the two-root-causes entry
+  above); the inline-path-as-filesystem-path `references` shape 500s (see Tried
+  and abandoned). Corrected vram
   4→24 GB, cold_start 8→240s, seedable false→true. Added 3 consenting
   British-female VCTK voices (Imogen=p225/Eleanor=p228/Beatrice=p229).
 
@@ -256,9 +273,10 @@ _25 older entries archived to archival-memory.md._
 
 - `[2026-06-01]` **Fish path-form references** (`{audio:"/app/references/x.wav"}`)
   → HTTP 500 on this build, despite the stack README showing that shape. The
-  working clone paths are `reference_id` (by name → reads `<name>.wav` +
+  working clone paths are `reference_id` (by name → resolves the DIRECTORY
-  optional `<name>.txt`) or inline base64 `references`. The catalog now uses
+  `references/<name>/` containing `<name>.wav` + `<name>.lab`; the flat
-  `reference_id`.
+  `references/<name>.wav` is ignored — see the two-root-causes entry above) or
+  inline base64 `references`. The catalog uses `reference_id`.
 
 - `[2026-06-01]` **Reference transcript barely affects Fish clone IDENTITY**
   (disproving my mid-session theory). I'd blamed a bogus provenance-note `.txt`

playbooks/deploy-fish-s2.yaml

@@ -36,6 +36,27 @@ steps:
     shell: mkdir -p {{ references_dir }}
     creates: "{{ references_dir }}"
 
+  - name: Normalize reference layout (flat <name>.wav → <name>/<name>.wav + .lab)
+    # fish-speech resolves reference_id=<name> against the DIRECTORY
+    # references/<name>/ (audio + a same-basename .lab transcript), NOT a
+    # flat references/<name>.wav. A flat-only layout makes every
+    # reference_id silently resolve to nothing → Fish falls back to its
+    # default speaker, so every voice in the dropdown sounds identical
+    # (this was the 2026-06-01 "no accent" root cause). External voice
+    # imports drop flat <name>.wav + <name>.txt here; this step mirrors
+    # each into references/<name>/<name>.wav + <name>/<name>.lab. `cp -u`
+    # makes it idempotent; the `when:` skips it once every flat wav has a
+    # matching nested wav (audio-only voices like glados need no .lab).
+    shell: |
+      cd {{ references_dir }} || exit 1
+      for w in *.wav; do
+        [ -e "$w" ] || continue
+        n="${w%.wav}"; mkdir -p "$n"
+        cp -u "$w" "$n/$n.wav"
+        [ -e "$n.txt" ] && cp -u "$n.txt" "$n/$n.lab" || true
+      done
+    when: "[ \"$(cd {{ references_dir }} 2>/dev/null && ls *.wav 2>/dev/null | wc -l)\" -ne \"$(cd {{ references_dir }} 2>/dev/null && ls */*.wav 2>/dev/null | wc -l)\" ]"
+
   - name: Ensure checkpoints dir exists
     shell: mkdir -p {{ checkpoints_dir }}
     creates: "{{ checkpoints_dir }}"
@@ -106,9 +127,10 @@ verify:
   - name: /v1/tts returns a real WAV (POST with text body)
     # Fish's API is NOT OpenAI-compatible — there's no /v1/audio/speech
     # and no /v1/audio/voices. The single TTS endpoint is POST /v1/tts
-    # with at minimum {"text":"..."} returning audio/wav. Voice cloning
+    # with at minimum {"text":"..."} returning audio/wav. Named-voice
-    # is via reference= field in the body (paths under /app/references).
+    # cloning is via the reference_id field, which resolves against the
-    # Verify by POST + asserting the response is a real RIFF WAV.
+    # references/<name>/ directory (audio + .lab) — see the A/B gate
+    # below. Verify by POST + asserting the response is a real RIFF WAV.
     shell: |
       out=$(mktemp --suffix=.wav)
       curl -sf -X POST http://localhost:{{ host_port }}/v1/tts \
@@ -119,6 +141,23 @@ verify:
       rm -f "$out"
     changed_when: "false"
 
+  - name: reference_id actually changes the voice (A/B — guards the empty-dir regression)
+    # Two different reference_ids with identical text+seed MUST yield
+    # different audio. If byte-identical, reference_id is being ignored
+    # (empty references/<id>/ dirs) and every voice has silently
+    # collapsed to Fish's default speaker — the 2026-06-01 root cause.
+    # Hard-fail the deploy so the regression can never ship silently.
+    shell: |
+      a=$(mktemp); b=$(mktemp)
+      curl -sf -X POST http://localhost:{{ host_port }}/v1/tts -H 'Content-Type: application/json' \
+        -d '{"text":"The quick brown fox.","seed":42,"reference_id":"Abigail"}' -o "$a" --max-time 60
+      curl -sf -X POST http://localhost:{{ host_port }}/v1/tts -H 'Content-Type: application/json' \
+        -d '{"text":"The quick brown fox.","seed":42,"reference_id":"Imogen"}' -o "$b" --max-time 60
+      rc=0; [ "$(md5sum < "$a")" = "$(md5sum < "$b")" ] && rc=1
+      rm -f "$a" "$b"
+      exit $rc
+    changed_when: "false"
+
   - name: Container is running
     shell: docker inspect fish-s2 --format '{{.State.Status}}' | grep -q running
     changed_when: "false"

stacks/fish-s2/README.md

@@ -94,10 +94,22 @@ root path; there's no `/openapi.json` endpoint exposed directly.
 
 ## Voice library
 
-Drop reference WAV / MP3 / FLAC into
+Named voices are selected via the `reference_id` field, which Fish
-`/worktank/fish-s2/references/` on the host. The wrapper scans on
+resolves against the **directory** `references/<name>/` — NOT a flat
-request — no restart needed. Use clean ~5-15 s clips, single
+`references/<name>.wav`. Stage each voice as:
-speaker, ideally with diverse intonation samples.
+
+```
+/worktank/fish-s2/references/<name>/<name>.wav   # clean ~5-15 s, single speaker
+/worktank/fish-s2/references/<name>/<name>.lab   # transcript of that clip
+```
+
+A flat `references/<name>.wav` (or an empty `references/<name>/` dir)
+is **silently ignored** — `reference_id` resolves to nothing and Fish
+falls back to its default speaker, so every voice sounds identical.
+This was the 2026-06-01 "no accent" root cause; the deploy playbook now
+carries a normalize-layout step + an A/B smoke gate (`reference_id`
+MUST change the output) to keep it from regressing. The wrapper scans
+on request — no restart needed after adding a voice.
 
 ## Deploy