fix(litellm): repoint TTS aliases at irv-ml1 via DNS name + extra_hosts

ext-tts / tts-1 / tts-1-hd / gpt-4o-mini-tts (all openai/zonos) were pinned to
irv-ml1's pre-move address 10.100.79.3:8198, dead since the 2026-09-06 headscale
cutover to 10.6.110.50 — so ext-tts through the gateway hung. Reported by
tts-dev/svos-dev.

The 4 aliases are DB-backed (store_model_in_db), so their api_base was updated
via the admin API to the DNS name http://irv-ml1.nh3.internal:8198/v1 (not a
fresh IP — that just re-arms the trap on the next move). The container cannot
resolve *.nh3.internal via split-horizon DNS, so this adds an extra_hosts entry
mapping the name to 10.6.110.50. Verified: container resolves the name and a
live ext-tts/sindra call returns 200 + valid MP3.

stacks/litellm/compose.yaml

@@ -28,6 +28,13 @@ services:
     image: ghcr.io/berriai/litellm:${LITELLM_TAG:-main-stable}
     container_name: litellm
     restart: unless-stopped
+    # irv-ml1 moved 10.100.79.3 -> 10.6.110.50 on 2026-09-06 (headscale
+    # cutover). The container cannot resolve *.nh3.internal via split-horizon
+    # DNS, so map the fleet-TTS gateway name here rather than re-hardcoding an
+    # IP in the DB model configs (ext-tts / tts-1 / tts-1-hd / gpt-4o-mini-tts,
+    # all openai/zonos). Update this IP if irv-ml1 moves again.
+    extra_hosts:
+      - "irv-ml1.nh3.internal:10.6.110.50"
     ports:
       - "${LITELLM_BIND:-0.0.0.0}:${LITELLM_PORT:-4000}:4000"
     volumes: