apiVersion: lumbridge/v1
kind: Scene
metadata:
  name: stock
  version: 1
  description: "The default scene: long-context brain, eyes, ears, and both narrators."
  author: karti
  tags: [brain, voice, long-context]

# Created 2026-08-16. THIS IS THE DEFAULT SCENE as of 2026-08-16 — it is what
# the box should be running unless someone is deliberately doing something else.
# Five models, chosen for capability rather than latency:
#
#   brain-nemotron-128k  41 GB  Lightning 30B at 128k   (measured 40.1)
#   ears                 10 GB  streaming ASR, self-limiting at 6m39s of audio
#                                                        (measured 9.9)
#   voice-vox            20 GB  VoxCPM 2 at cfg 3.0 / 20 steps, capped at 3600 chars
#   eye                  14 GB  Cosmos 3 Edge, still frames only  (measured 11.8)
#   voice                 5 GB  Chatterbox TURBO on :8095   (measured 3.2 GPU)
#                               ⚠️ but it LEAKS HOST RAM - see the registry
#                        ----
#                        90 GB committed against a 100 GB budget.
#
# All footprints above were measured 2026-08-16 with
# `nvidia-smi --query-compute-apps`, NOT RSS — RSS does not see GPU memory on
# this unified-memory box (the brain reads 8 GB RSS against 40 GB actual).
#
# TWO NARRATORS, ON PURPOSE. VoxCPM (:8096) is the quality narrator but is
# SLOWER THAN REAL TIME: measured RTF 1.54-1.91 warm, 3.07 cold, against the
# 1.62 recorded at build. Chatterbox turbo (:8095) is RTF ~0.26. So:
#   - anything in a request path -> :8095
#   - anything offline where quality wins -> :8096
# Chatterbox is also here because audiobook and downstream voice services
# all hardcode :8095; dropping it on 2026-08-16 took all three down until it
# was restored here the same day. VoxCPM is NOT a drop-in for them - different
# protocol, different voice registry.
#
# The Chatterbox FULL checkpoint is sunset as of 2026-08-16; `voice` is
# turbo-only and the /voice A/B Lab's `full` option now 400s. See the registry.
#
# 256k -> 128k to make room for the eye: at 57 GB the brain plus the eye needed
# 104 GB against a 100 GB budget and the Governor refused the admit.
models:
  - brain-nemotron-128k
  - ears
  - voice-vox
  - eye
  - voice


budget_gb: 100
activation:
  order: footprint-asc   # the small services up first; the 41 GB brain last
  wait_healthy: true