Keysat
7ae6ab3ba8
GPU-arbiter safety layer for when automation, not just the dashboard, swaps models: - swap reservation lock (POST/GET/DELETE /api/swap/lock); 423-enforced in post_swap via a single-read gate, TTL-bounded, secret-token auth, human force-release override + dashboard banner - swap webhook (swap_complete/swap_failed) fired outside the swap lock, optional HMAC signature, configurable URL+secret - read-only schedule registry (GET/POST/DELETE /api/schedule) + dashboard panel New module image/app/coordination.py; docs/COORDINATION.md for consumers; 22 offline tests in test_coordination.py.
51 lines
2.1 KiB
TypeScript
51 lines
2.1 KiB
TypeScript
import { FileHelper } from '@start9labs/start-sdk'
|
|
import { z } from 'zod'
|
|
import { sdk } from '../sdk'
|
|
|
|
export const sparkConfigSchema = z.object({
|
|
spark1_host: z.string().catch(''),
|
|
spark1_user: z.string().catch(''),
|
|
spark2_host: z.string().catch(''),
|
|
spark2_user: z.string().catch(''),
|
|
// Optional vLLM port override (Spark 1). Blank => 8888 (launch-cluster.sh default).
|
|
vllm_port: z.string().catch(''),
|
|
// Optional vLLM container-name override (Spark 1). Blank => "vllm_node".
|
|
vllm_container: z.string().catch(''),
|
|
// Optional comma-separated list of built-in services to switch off
|
|
// (parakeet, kokoro, embeddings, qdrant). Blank => all enabled.
|
|
disabled_services: z.string().catch(''),
|
|
// Optional per-service overrides. Blank => use spark2_host / spark2_user.
|
|
parakeet_host: z.string().catch(''),
|
|
parakeet_user: z.string().catch(''),
|
|
parakeet_container: z.string().catch(''),
|
|
kokoro_host: z.string().catch(''),
|
|
kokoro_user: z.string().catch(''),
|
|
kokoro_container: z.string().catch(''),
|
|
// Optional overrides for the embedding server (spark-embed) + Qdrant.
|
|
embed_host: z.string().catch(''),
|
|
embed_user: z.string().catch(''),
|
|
embed_container: z.string().catch(''),
|
|
qdrant_host: z.string().catch(''),
|
|
qdrant_user: z.string().catch(''),
|
|
qdrant_container: z.string().catch(''),
|
|
qdrant_collection: z.string().catch(''),
|
|
// Optional matrix-bridge bot. Blank => no tile. Host reuses Spark 2.
|
|
matrix_bridge_user: z.string().catch(''),
|
|
// Optional Open WebUI deep-link
|
|
open_webui_url: z.string().catch(''),
|
|
// Optional NGC API key for pulling NIM containers from nvcr.io/nim/...
|
|
ngc_api_key: z.string().catch(''),
|
|
// Optional coordination webhook: POSTed on swap_complete/swap_failed so
|
|
// downstream consumers re-point their model config. Blank => disabled.
|
|
swap_webhook_url: z.string().catch(''),
|
|
// Optional shared secret; if set, the webhook body is HMAC-signed.
|
|
swap_webhook_secret: z.string().catch(''),
|
|
})
|
|
|
|
export type SparkConfig = z.infer<typeof sparkConfigSchema>
|
|
|
|
export const sparkConfigYaml = FileHelper.yaml(
|
|
{ base: sdk.volumes.main, subpath: 'config.yaml' },
|
|
sparkConfigSchema,
|
|
)
|