mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-31 21:49:52 +00:00
e2564d8358
Implements full MCP SSE decoupling to eliminate recurring outages: 1. ruvbrain-sse: Thin SSE proxy (308 lines) that manages MCP connections independently from the API. Max 200 concurrent SSE, forwards JSON-RPC to the API, polls /internal/queue/drain for responses. No business logic. 2. ruvbrain-worker: Batch worker binary (202 lines) for Cloud Run Jobs. Runs scheduler actions (train, drift, transfer, graph, cleanup, attractor) with direct Firestore access. Runs once and exits. 3. Internal queue endpoints on the API: - POST /internal/queue/push (forward JSON-RPC to session) - GET /internal/queue/drain (poll for responses) - POST /internal/session/create (register session) - DELETE /internal/session/:id (cleanup) 4. Deploy infrastructure: - Dockerfile.sse, Dockerfile.worker - cloudbuild-sse.yaml, cloudbuild-worker.yaml - scripts/deploy_brain_services.sh [api|sse|worker|all] Architecture: SSE (500 concurrency, 512MB) → API (80 concurrency, 4GB) ← Worker (Cloud Run Job, 4GB) Co-Authored-By: claude-flow <ruv@ruv.net>
70 lines
2.3 KiB
Bash
Executable file
70 lines
2.3 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
# Deploy ADR-130 brain service split
|
|
# Usage: ./scripts/deploy_brain_services.sh [api|sse|worker|all]
|
|
|
|
PROJECT=ruv-dev
|
|
REGION=us-central1
|
|
|
|
deploy_api() {
|
|
echo "=== Deploying ruvbrain-api ==="
|
|
gcloud builds submit --config=crates/mcp-brain-server/cloudbuild.yaml --project=$PROJECT
|
|
gcloud run deploy ruvbrain \
|
|
--image=gcr.io/$PROJECT/ruvbrain:latest \
|
|
--region=$REGION \
|
|
--memory=4Gi --cpu=2 \
|
|
--concurrency=80 --max-instances=15 --min-instances=1 \
|
|
--timeout=300 --session-affinity \
|
|
--allow-unauthenticated
|
|
}
|
|
|
|
deploy_sse() {
|
|
echo "=== Deploying ruvbrain-sse ==="
|
|
# Build SSE image
|
|
gcloud builds submit \
|
|
--config=crates/mcp-brain-server/cloudbuild-sse.yaml \
|
|
--project=$PROJECT
|
|
# Deploy SSE service
|
|
gcloud run deploy ruvbrain-sse \
|
|
--image=gcr.io/$PROJECT/ruvbrain-sse:latest \
|
|
--region=$REGION \
|
|
--memory=512Mi --cpu=1 \
|
|
--concurrency=500 --max-instances=10 --min-instances=0 \
|
|
--timeout=3600 --session-affinity \
|
|
--allow-unauthenticated \
|
|
--set-env-vars="BRAIN_API_URL=https://ruvbrain-HASH.us-central1.run.app,RUST_LOG=info"
|
|
# Note: BRAIN_API_URL needs the actual Cloud Run URL of ruvbrain-api
|
|
}
|
|
|
|
deploy_worker() {
|
|
echo "=== Deploying ruvbrain-worker ==="
|
|
# Build worker image
|
|
gcloud builds submit \
|
|
--config=crates/mcp-brain-server/cloudbuild-worker.yaml \
|
|
--project=$PROJECT
|
|
# Create Cloud Run Job (not a service)
|
|
gcloud run jobs create ruvbrain-worker \
|
|
--image=gcr.io/$PROJECT/ruvbrain-worker:latest \
|
|
--region=$REGION \
|
|
--memory=4Gi --cpu=2 \
|
|
--max-retries=1 --task-timeout=3600s \
|
|
--set-env-vars="RUST_LOG=info" \
|
|
--set-secrets=BRAIN_API_KEY=brain-api-key:latest,BRAIN_SIGNING_KEY=brain-signing-key:latest \
|
|
2>/dev/null || \
|
|
gcloud run jobs update ruvbrain-worker \
|
|
--image=gcr.io/$PROJECT/ruvbrain-worker:latest \
|
|
--region=$REGION \
|
|
--memory=4Gi --cpu=2
|
|
}
|
|
|
|
# Parse argument
|
|
case "${1:-all}" in
|
|
api) deploy_api ;;
|
|
sse) deploy_sse ;;
|
|
worker) deploy_worker ;;
|
|
all) deploy_api && deploy_sse && deploy_worker ;;
|
|
*) echo "Usage: $0 [api|sse|worker|all]"; exit 1 ;;
|
|
esac
|
|
|
|
echo "=== Done ==="
|