feat(observability+tts): OTel logs for backend/runner/ui; add kokoro-fastapi (GPU) and pocket-tts (CPU) to homelab

- otelsetup.Init now returns a *slog.Logger wired to the OTLP log exporter
  so all slog output is shipped to Loki with embedded trace IDs
- backend and runner both adopt the new OTel-bridged logger
- runner.runScrapeTask and runAudioTask now emit structured OTel spans
- ui/hooks.server.ts adds BatchLogRecordProcessor alongside existing trace exporter
- homelab: add kokoro-fastapi GPU service (ghcr.io/remsky/kokoro-fastapi-gpu)
  using deploy.resources.reservations for NVIDIA GPU, exposed internally on :8880
- homelab: add pocket-tts CPU service (ghcr.io/kyutai-labs/pocket-tts) on :8000
- runner KOKORO_URL hardcoded to http://kokoro-fastapi:8880 (fixes DNS failure
  for the stale kokoro.kalekber.cc hostname)

homelab/docker-compose.yml

@@ -58,7 +58,7 @@ services:
       VALKEY_ADDR: ""
       GODEBUG: "preferIPv4=1"
 
-      KOKORO_URL: "${KOKORO_URL}"
+      KOKORO_URL: "http://kokoro-fastapi:8880"
       KOKORO_VOICE: "${KOKORO_VOICE}"
 
       RUNNER_WORKER_ID: "${RUNNER_WORKER_ID}"
@@ -386,6 +386,48 @@ services:
       timeout: 5s
       retries: 5
 
+  # ── Kokoro-FastAPI (GPU TTS) ────────────────────────────────────────────────
+  # OpenAI-compatible TTS service backed by the Kokoro model, running on the
+  # homelab RTX 3050 (8 GB VRAM). Replaces the broken kokoro.kalekber.cc DNS.
+  # Voices match existing IDs: af_bella, af_sky, af_heart, etc.
+  # The runner reaches it at http://kokoro-fastapi:8880 via the Docker network.
+  kokoro-fastapi:
+    image: ghcr.io/remsky/kokoro-fastapi-gpu:latest
+    restart: unless-stopped
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    expose:
+      - "8880"
+    healthcheck:
+      test: ["CMD", "curl", "-sf", "http://localhost:8880/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 60s
+
+  # ── pocket-tts (CPU TTS) ────────────────────────────────────────────────────
+  # Lightweight CPU-only TTS using kyutai-labs/pocket-tts.
+  # OpenAI-compatible: POST /v1/audio/speech on port 8000.
+  # Voices: alba, marius, javert, jean, fantine, cosette, eponine, azelma.
+  # Not currently used by the runner (runner uses kokoro-fastapi), but available
+  # for experimentation / fallback.
+  pocket-tts:
+    image: ghcr.io/kyutai-labs/pocket-tts:latest
+    restart: unless-stopped
+    expose:
+      - "8000"
+    healthcheck:
+      test: ["CMD", "curl", "-sf", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 60s
+
   # ── Watchtower ──────────────────────────────────────────────────────────────
   # Auto-updates runner image when CI pushes a new tag.
   # Only watches services with the watchtower label.