feat(morpheus): staged clone voices + max_tokens 3500 (context-clamped)

- max_tokens default 2400->3500 (~42s) in wrapper + gateway-chat client, with a _cap()
  clamp so prompt+gen never exceeds MAX_CTX (4096) — a cloning ref block is ~1100 tokens,
  so an unclamped 3500 would overflow context on the clone path.
- Staged clone voices: /voices dir of <name>.wav + <name>.txt, each encoded to its Orpheus
  reference block at startup; voice="<name>" zero-shot clones it. Beatrice (a chatterbox
  reference) staged as the first normal-voice clone. GET /voices lists baddy + clones.
- compose: mount voices dir + pass MORPHEUS_MAX_LEN to the wrapper (clamp must match engine).

vLLM concurrency (measured, --max-num-seqs 8, 250-tok reqs): near-linear batching — 8
concurrent finish in the same ~2.8s as 1 (707 tok/s, 8.1x single, flat per-req latency).
Chunked-sentence production can fan out for ~8x throughput; CPU SNAC decode is the scale
bottleneck, not generation.

stacks/mOrpheus/compose.yaml

@@ -67,9 +67,12 @@ services:
       - SNAC_DEVICE=cpu
       - MORPHEUS_DEFAULT_VOICE=${MORPHEUS_DEFAULT_VOICE:-baddy}
       - MORPHEUS_VOICES=${MORPHEUS_VOICES:-baddy}
+      - MORPHEUS_VOICES_DIR=/voices          # <name>.wav + <name>.txt => voice="<name>" clones it
+      - MORPHEUS_MAX_LEN=${MORPHEUS_MAX_LEN:-4096}   # must match engine --max-model-len (max_tokens clamp)
     volumes:
       - ${MORPHEUS_MODEL_DIR:-/home/lkraven/morpheus/models/mOrpheus}:/model:ro
       - ${SNAC_DIR:-/home/lkraven/morpheus/models/snac_24khz}:/snac:ro
+      - ${MORPHEUS_VOICES_DIR:-/home/lkraven/morpheus/voices}:/voices:ro
     ports:
       - "${MORPHEUS_TTS_PORT:-8299}:8000"
     healthcheck: