Method track

core/services/nodes/inflight.go:67–81

(ctx context.Context)

}

func (c *InFlightTrackingClient) track(ctx context.Context) func() {
	if err := c.registry.IncrementInFlight(ctx, c.nodeID, c.modelName, c.replicaIndex); err != nil {
		xlog.Warn("Failed to increment in-flight counter", "node", c.nodeID, "model", c.modelName, "replica", c.replicaIndex, "error", err)
		return func() {}
	}
	return func() {
		decCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
		defer cancel()
		c.registry.DecrementInFlight(decCtx, c.nodeID, c.modelName, c.replicaIndex)
		// Release the initial reservation after the first inference call completes
		if c.onFirstComplete != nil {
			c.firstOnce.Do(c.onFirstComplete)
		}
	}
}

// reconcile self-heals stale routing: when a backend reports that the model is
// no longer loaded (the process survived but the model was evicted, while the