memory: snapshot — R17 audition concluded → Zonos productionized (zonos-gateway shipped + online in asset-engine); omnivoice retired, vllm-morpheus killed, ComfyUI down/parked

persistent-memory.md

@@ -1,6 +1,6 @@
 # Persistent memory — eshpfi-management
 
-_Last updated: 2026-07-10_
+_Last updated: 2026-07-11_
 
 ## Repo purpose
 
@@ -102,39 +102,55 @@ no longer deployed sidecars here. See Recent decisions.)
 
 ## Current state / in-flight
 
-_As of 2026-07-10 — session ran three Vuong-authorized peer tasks: brokkr TTS audition (DELEGATED, in-flight),
-comfy-dev ComfyUI bump (attempted → ROLLED BACK, blocked on comfy-dev), biweekly scan cron (SETTLED). Full detail
-in the 2026-07-10 Recent-decisions entries. Immediate fresh-context pickup:_
+_As of 2026-07-11 — the R17 TTS audition CONCLUDED and **Zonos was productionized** (won the expressive tier →
+shipped as the `zonos-gateway` stack, below). Fleet changes this session: **omnivoice RETIRED**, **vllm-morpheus
+KILLED** (operator: unimpressive), **ComfyUI TAKEN DOWN** (A6000 freed for the audition; comfy-dev PARKED — the
+v0.27.1 bump it validated stays LANDED, just not running). **Higgs** auditioned well + streams (room in the zoo)
+but is PARKING-LOT, not shipped. Immediate fresh-context pickup:_
 
-- **🔊 TTS AUDITION (research-slot) — env+harness build DELEGATED to a background agent (IN-FLIGHT).** Stand up
-  Higgs TTS 3 (`bosonai/higgs-tts-3-4b`, ungated despite NC) + ZONOS2 (`Zyphra/ZONOS2`, Apache) + Chatterbox
-  baseline (already running `chatterbox-fast` :8197) on irv-ml1's **A6000** (~30G free; 3090 full w/ mOrpheus),
-  SEQUENTIAL load. Harness = text→WAV per model + **TTFA/RTF** logging. Protocol (READ IT):
-  `~/development/brokkr-smithy/research/R17-nvv-extraction/erp-voice-nvv-corpus/tts-audition-protocol.md`. Decider =
-  NVV/expressive naturalness; deliver blind-A/B web-listen + latency table → **operator ranks** (not me). brokkr
-  delivers the ~15-20 prompt set AFTER the env's up. **⚠️ FRESH-CONTEXT PICKUP: a background general-purpose agent
-  (spawned 2026-07-10) is doing the build; its WORK persists on irv-ml1 but its completion-ping/agent-ID likely
-  won't route post-/clear → on resume VERIFY the build state DIRECTLY on irv-ml1 (`ssh irv-ml1`; look for a
-  `tts-audition` work area under /worktank or /home/lkraven, pulled models, the harness) instead of waiting for the
-  agent.** irv-ml1 = lkraven, docker-group, NO sudo; A6000 = docker device 1.
+- **🗣️ ZONOS-GATEWAY TTS — SHIPPED + ONLINE (irv-ml1), the R17 expressive winner.** Two pieces. (1) **Zonos
+  engine** — native zonos2 server (`Zyphra/ZONOS2`, Apache), bare `python3` on irv-ml1 **:1920**, on the **3090**
+  (operator moved it here off the retired omnivoice); streams float32 PCM @44.1kHz via `POST /tts/generate`;
+  emotion = **embedding-direction conditioning (NOT tags)** + **clone-gated** (no-ops without a speaker ref);
+  vendored copy kept **STOCK**. (2) **zonos-gateway wrapper** — OpenAI `/v1/audio/speech` facade over the native
+  endpoint, **containerized** at `/opt/docker/compose/zonos-gateway/` (image `zonos-gateway:0.2.0`,
+  `restart: unless-stopped`, reaches host Zonos via `host.docker.internal:1920`), **:8890**, default voice **Cora**
+  (voices = `*.wav` baked into the image). Full **24-dial** expressive surface + presets
+  (neutral/warm/excited/sad/intense/whisper) via `GET /v1/dials`; `response_format` pcm|wav. Repo
+  `~/development/zonos-gateway` (v0.2.0, LOCAL git only). **In asset-engine catalog**
+  (`docs/asset-engine/services.yaml`, id `zonos-gateway`, status experimental) → shows **online** (background poller
+  auto-adopts the running container, NO VRAM gate, NO `/start`) → experiment at
+  `http://10.250.50.70:8200/ui/stream-audition/zonos-gateway`. **gateway-chat** (ana-docker:8091) repointed DIRECT
+  to it (OpenAI body, Cora, streamed, quotes joined not chunked). ⚠️ **NEVER expose the rep-penalty dials**
+  (50/1.2/8 — LOAD-BEARING; OFF → 70s-silence footgun). Auto-memory `reference_zonos_tts_stack`. **PENDING
+  close-outs:** (a) repoint LiteLLM `ext-tts` alias → the wrapper (generic hot-swap point; NOTE LiteLLM buffers
+  audio → streaming needs a DIRECT wrapper hit, not through `ext-tts`); (b) revert vendored Zonos `api_server.py`
+  OpenAI-endpoint patches to STOCK (rep-penalty + `_voice_to_speaker_id` + Cora reg; `.bak-*-20260710` on irv-ml1 —
+  the wrapper made them redundant); (c) cosmetic: catalog `model.image` reads `local/zonos-gateway:0.1.0`, reality
+  `zonos-gateway:0.2.0` — reconcile on next catalog touch (a resync bounces the live lab). Old bare-deploy dir
+  `/home/lkraven/zonos-gateway` on irv-ml1 = idle cruft.
 
-- **🖼️ COMFYUI BUMP → v0.27.1 — comfy-dev GAVE THE GO + FULL RECIPE (2026-07-10); re-attempt on fresh context.**
-  Target CORRECTED to **v0.27.1** (the ACTUAL latest; operator said "v25" but wants latest + Krea-2 needs ≥0.25 so
-  0.27.1 covers it; braced for breakage). irv-ml1 `comfyui` currently healthy on rolled-back 0.24.1. Prior attempt
-  crash-looped (SageAttention ABI vs torch 2.13; DISABLE_UPGRADES bumped the venv but NOT the ComfyUI git checkout
-  — see the 2026-07-10 Recent-decisions entry). **comfy-dev's atomic recipe (althing thread 01KX655V — run "your
-  way", bundle to avoid a broken intermediate):** (1) git-advance `/comfy/mnt/ComfyUI` → tag **v0.27.1** +
-  `pip install -r requirements.txt` **as uid 1000** for new deps; (2) torch 2.13.0 rides along (expected, for LTX);
-  (3) **rebuild SageAttention vs torch 2.13.0** so `--use-sage-attention` works — IF the recompile fights, DROP the
-  flag as fallback + **FLAG comfy-dev** (SageAttn is load-bearing for WAN speed + tied to their per-workflow
-  AttentionSelector workaround for the Qwen-black bug, so they re-validate); (4) re-pin `DISABLE_UPGRADES=true`. Net
-  = `/worktank/comfyui/venv-snapshot-comfyui-0.24.1-20260710.tar` (crash-loop → roll back like last time + ping).
-  **PING comfy-dev when healthy on 0.27.1** → they run their 3-tier validation (node-schema diff vs their saved
-  105-node baseline → validate_graph_templates.py → smoke renders across families) + own the workflow-breakage
-  triage. Optional: add `decord` (uid 1000) for the pre-existing ComfyUI-RMBG SAM3Segment warning if trivial, else
-  skip. **⚠️ comfy-dev's GO is currently UNACKED; it's a RISKY re-attempt (crash-looped once) and the operator said
-  "wait for comfy… before WE go back" → the fresh context should SURFACE to the operator (comfy-dev GO'd + v0.27.1
-  recipe ready) and confirm before executing, NOT silently auto-run.**
+- **🔊 R17 TTS AUDITION — CONCLUDED (operator ranked live).** 3-model expressive audition
+  (Chatterbox-fast / ZONOS2 / Higgs-v3) on irv-ml1's A6000 (ComfyUI taken down to free it). **Latency smoke**
+  (`~/tts-audition/records/latency.csv`): Chatterbox TTFA 0.47–0.80s / RTF 0.28–0.38 (24kHz streamed — fastest,
+  stays the low-latency front-end); ZONOS2 warm TTFA ~8s / RTF 2.79 (44.1kHz, clone-gated emotion); Higgs whole-file
+  TTFA≈gen 2.6–2.8s / RTF 0.98 (NOT streamed — footnote, not comparable to the streamed two). **Outcome: Zonos
+  productionized** for the expressive tier (see zonos-gateway above); **Higgs = parking-lot** (streams, room in the
+  zoo, not shipped — Path-A in-process build preserved at `~/tts-audition/`: venv `venvs/higgs`, transformers 5.5.0,
+  `harness/higgs_native.py`, Qwen3-4B backbone + baked codec; revisit if wanted). **Chatterbox-fast** stays the
+  low-latency front-end. Protocol: brokkr-smithy R17 `tts-audition-protocol.md`.
+
+- **🖼️ COMFYUI — v0.27.1 LANDED + comfy-dev-VALIDATED, now TAKEN DOWN (A6000 freed; comfy-dev PARKED).** The
+  v0.27.1 bump stays LANDED (validated clean by comfy-dev, thread 01KX6D3C — 3-tier sweep 189 graphs / 105
+  node-types, ZERO breakage, all 9 templates + smoke renders OK: Z-Image / FLUX.1-dev / Illustrious-SDXL /
+  FLUX.2-GGUF / Qwen-edit sage-AttentionSelector / LTX i2v). ComfyUI is just **not RUNNING** — operator took it down
+  to give the R17 audition the A6000. **Restart when comfy-dev un-parks.** Landed on the EXISTING **torch
+  2.12.1+cu129, SageAttention 2.2.0 intact** (deliberately did NOT bump torch — the 2.13 bump was the mmartial
+  boot-upgrade's ABI crash-loop cause, never an LTX requirement; **SETTLED = don't bump**). Mechanics: code
+  `/worktank/comfyui/run/ComfyUI` (=/comfy/mnt/ComfyUI in-container), `docker exec` lands as uid **1025** → use
+  `-u 1000` + venv python `/comfy/mnt/venv/bin/python` (venv owned lkraven:1000), `DISABLE_UPGRADES=true` pinned,
+  NVIDIA_VISIBLE_DEVICES=1 (A6000). Rollback net `/worktank/comfyui/venv-snapshot-comfyui-0.24.1-20260710.tar`. LTX
+  Phase-2 node-install = its own future thread (installs uid-1000).
 
 - **📅 BIWEEKLY LANDSCAPE-SCAN CRON — SETTLED.** Live systemd --user timer on nh3-dev (next auto-run 2026-07-15
   09:00 PT), dedicated `brokkr-scan-dev` handle, notify = `post --to brokkr-smithy-dev` (Vuong ruled inbox-post,
@@ -151,6 +167,8 @@ _As of 2026-07-09 — RP-seat 3-seat inference stack still COMPLETE + SETTLED (g
 char-rp-reasoning, detail below). NEW this session: a **mOrpheus TTS voice pipeline** shipped
 end-to-end (deployed on irv-ml1, voicing gateway-chat). Home-training dormant. Live state:_
 
+- **⚠️ SUPERSEDED 2026-07-11: vllm-morpheus KILLED (operator: unimpressive); gateway-chat is now voiced by
+  zonos-gateway (above), NOT mOrpheus. Block kept for the SNAC/clone-voice detail only.**
 - **🗣️ mOrpheus TTS — PERMANENT STACK DEPLOYED (irv-ml1), voicing gateway-chat.** Off-the-shelf
   uncensored Orpheus TTS (`MrDragonFox/mOrpheus_3B-1Base_early_preview-v1-25000`; Llama-3.2-3B LLM
   → SNAC 24kHz audio). Canonical `stacks/mOrpheus/`; deployed at `/home/lkraven/morpheus/` on irv-ml1.
@@ -346,6 +364,35 @@ _Earlier (2026-07-07):_
 
 ## Recent decisions
 
+- `[2026-07-10]` **Heimdall grant: ratatoskr `affect.full` on PERSONAL Worldtree (operator-approved, worldtree-dev
+  R34-v1 request).** Added allow-rule `ratatoskr-affect-full-allow` to `/opt/worldtree-personal/config/policies.yaml`
+  (`principal.user_ids:["ratatoskr"]`, action `affect.full`, resource `*`, effect allow), mirroring the #347
+  `session-history-write-ratatoskr` rule exactly + placed right after it. **WHY user_ids-based (not tier):** ratatoskr's
+  personal key is the minimal **readonly-admin** observability tier, which is NOT in the tier-based
+  `affect-render-baseline-allow` (anonymous/user/free/pro/admin) → needs an explicit user_id grant, same as #347.
+  R34-v1 (b46, committed UNPUSHED) gates `affect.emit` `dominant_emotion` egress by exposure ceiling (affect.full|safe
+  → present; neither → null); this grant keeps ratatoskr's view alive across the b46 deploy. Surgical exact-string
+  insert (preserves comments), backup `policies.yaml.bak-pre-affectfull-20260710`, validated via the CONTAINER's own
+  yaml parser (35 rules, +1, payload confirmed). **NOT restarted — deliberate:** rule is on the bind-mount (shadows
+  baked), INERT until b46 gating ships, so the b46 CI/CD deploy restart activates it (no live-session blip now). Demo
+  untouched (personal-only per key scope). Replied to wt-dev (thread 01KX6DB3…) offering an immediate restart if they
+  want it live for pre-b46 testing. See [[reference_corviduo_dev_emergency_ops]].
+
+- `[2026-07-10]` **ComfyUI v0.27.1 SUCCESS on irv-ml1 (operator-confirmed execute-now) — landed on torch 2.12.1,
+  SageAttention preserved, crash-loop AVOIDED.** The prior attempt (entry below) crash-looped because a torch
+  2.12.1→2.13 bump broke SageAttention's ABI. This time I checked `git diff v0.24.1 v0.27.1 -- requirements.txt`
+  FIRST and found **core v0.27.1 leaves `torch` UNPINNED** → the version bump does NOT require torch 2.13 (that came
+  only from the mmartial boot-upgrade). So: `git checkout v0.27.1` (clean tree) → `pip install -r requirements.txt`
+  as **uid 1000** with a **torch-pin constraint file** (torch/vision/audio pinned to current +cu129) to block any
+  transitive bump → torch stayed 2.12.1, SageAttention 2.2.0 untouched. Added decord 0.6.0 (fixed SAM3Segment).
+  `docker restart comfyui` → healthy, `/system_stats` comfyui_version=0.27.1, "Using sage attention", HTTP 200, DB
+  migrated 0003→0004. Reported the divergence to comfy-dev (thread 01KX6D3C…, reply pending) + asked whether LTXV 2.3
+  needs a separate torch-2.13 follow-up (their domain; Krea-2's ≥0.25 need is met by 0.27.1). **LESSON: before a
+  mmartial ComfyUI version bump, `git diff <old> <new> -- requirements.txt` — if torch is unpinned, bump the CODE
+  without touching torch (constraint-pin it) and compiled exts (SageAttention) survive. `docker exec` lands as uid
+  1025(comfytoo), not 1000 — use `-u 1000` + the venv python `/comfy/mnt/venv/bin/python`.** See
+  [[reference_irv_ml1_comfyui_mmartial]].
+
 - `[2026-07-10]` **ComfyUI 0.25.x bump on irv-ml1 ATTEMPTED → FAILED → ROLLED BACK (snapshot saved it).** comfy-dev
   requested (Vuong-authorized) bumping the irv-ml1 `comfyui` stack (mmartial image, `/opt/docker/compose/comfyui/`,
   0.24.1) to 0.25.x for Krea-2 + LTXV 2.3. **TWO FINDINGS: (1) `DISABLE_UPGRADES=false`/USE_PIPUPGRADE bumps the