fix: HA checks resolve service targets over project network; persist checks (#13)
CI / Infra (Compose + Scripts) (push) Canceled after 0s
CI / Backend (Go) (push) Canceled after 0s
CI / Frontend (React) (push) Canceled after 0s
CI / Compose boot smoke (push) Canceled after 0s
CI / Build & publish images (push) Canceled after 0s
CI / Release (push) Canceled after 0s

- Health checks for local services dialed 127.0.0.1 from inside the backend
  container — the host's published port is unreachable there. Service-bound
  checks now resolve the service's DNS name on its project network (backend
  joins on demand), falling back to the service's stored port. A resolver
  failure surfaces as TARGET_UNRESOLVED instead of a fake loopback probe.
- Checks lived only in memory: a backend restart silently deleted every
  configured health check. ha_health_checks table + write-through on
  add/update/tick and hydrate-on-boot, matching the scaling-policy pattern.
- sqlc schema.sql gained the runtime columns added by later migrations —
  the stale snapshot already caused one silently-dropped-column bug.
- OpenAPI: runtime response now documents ports and health fields; types
  regenerated.
- Buttons no longer wrap ("+ new project" rendered on two lines).

Verified live: service check probes whoami-web:80 via DNS → healthy;
check survives a backend restart and rehydrates.

Generated with [Devin](https://devin.ai)

Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Tomáš DvořákandDevin authored and GitHub committed 2026-10-04 09:37:47 +02:00
1 parent 32b52d121f
commit 15b5b0e6e7
8 files changed
+216 -21

No files matched your search

+27
View File
@@ -57,6 +57,33 @@ func SetupRoutes(router *gin.Engine, db *database.DB, redis *database.Redis, cfg
}
}
haManager := ha.NewHighAvailabilityManager(scheduler, metricsCollector)
if db != nil && db.DB != nil {
haManager.WithPersistence(db.DB)
if err := haManager.LoadHealthChecks(context.Background()); err != nil {
log.Printf("Failed to restore health checks: %v", err)
}
}
if dockerClient != nil && db != nil {
// Service-bound checks probe the service DNS name on the project
// network — the backend container joins it on demand. The old
// 127.0.0.1 fallback stays for node-bound checks.
docker := dockerClient
haManager.WithServiceResolver(func(ctx context.Context, serviceID string) (string, int, error) {
var name, projectID string
var port int
err := db.QueryRowContext(ctx,
`SELECT name, project_id::text, COALESCE(port, 0) FROM services WHERE id = $1`,
serviceID,
).Scan(&name, &projectID, &port)
if err != nil {
return "", 0, err
}
if err := docker.ConnectSelfToNetwork(ctx, deployment.ProjectNetworkName(projectID)); err != nil {
return "", 0, err
}
return name, port, nil
})
}
haAPIManager := NewHAManager(haManager)
// Initialize scaling handler