v0.13.0:4 - redaction gateway, embeddings proxy, expanded audio API

- Add redaction gateway (redaction_gateway.py, redaction/ scrub + tests)
- Add embeddings proxy and spark_embed service (Dockerfile + main.py)
- Expand audio_proxy with speaker-aware handling; deep_health/health/server updates
- Package: configureSparks action + sparkConfig model updates, manifest/main wiring
- Docs: AUDIO_API, EMBEDDINGS, REDACTION_GATEWAY; HANDOFF and runbook/known-issues refresh

package/startos/interfaces.ts

@@ -22,7 +22,7 @@ export const setInterfaces = sdk.setupInterfaces(async ({ effects }) => {
     name: i18n('OpenAI-compatible API'),
     id: 'api',
     description: i18n(
-      'Service-discovery JSON at /api/endpoints. Other apps on the LAN can GET this to learn the current vLLM, Parakeet, and Magpie URLs.',
+      'Service-discovery JSON at /api/endpoints. Other apps on the LAN can GET this to learn the current vLLM, Parakeet, and Kokoro URLs.',
     ),
     type: 'api',
     masked: false,