Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cmd/atenet/internal/router/cmd.go
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ func NewRouterCmd() *cobra.Command {
cmd.Flags().BoolVar(&cfg.Auth.AteapiUseTokenAuth, "ateapi-use-token-auth", false, "Authenticate to ateapi with the Bearer token from --ateapi-token-file instead of the client certificate from --ateapi-client-cert.")
cmd.Flags().StringVar(&cfg.Auth.AteapiTokenFile, "ateapi-token-file", "", "Projected SA token file used as Bearer credential. Required with --ateapi-use-token-auth, ignored otherwise.")
cmd.Flags().DurationVar(&cfg.RouteTimeout, "route-timeout", defaultRouteTimeout, "Envoy's end-to-end timeout on the workload route, bounding one request from the ingress listener to the actor's response. Raise it for actors whose turns legitimately run long — a harness relaying an LLM completion holds the request open for the whole generation. This does not cover the resume that may precede the request; see --parked-request-budget")
cmd.Flags().DurationVar(&cfg.ParkedRequest.Budget, "parked-request-budget", ingress.DefaultParkedRequestBudget, "Maximum time a resume flight keeps a request parked (held and retried) waiting for its actor to become routable; concurrent requests for the same actor share one flight and its budget")
cmd.Flags().DurationVar(&cfg.ParkedRequest.Budget, "parked-request-budget", ingress.DefaultParkedRequestBudget, "Maximum time each request is parked (held and retried) waiting for its actor to become routable; concurrent requests for the same actor share a control-plane retry loop without sharing wait budgets")
cmd.Flags().IntVar(&cfg.ParkedRequest.Max, "parked-request-max", ingress.DefaultParkedRequestMax, "Maximum number of requests that may be parked simultaneously; excess requests are shed with 503. 0 disables parking (requests fail fast on worker-pool saturation)")
cmd.Flags().DurationVar(&cfg.ParkedRequest.RetryInterval, "parked-request-retry-interval", ingress.DefaultParkedRequestRetryInterval, "Delay before a parked request's first resume retry")
cmd.Flags().Float64Var(&cfg.ParkedRequest.RetryFactor, "parked-request-retry-factor", ingress.DefaultParkedRequestRetryFactor, "Multiplier applied to the retry delay after each attempt; must be >= 1")
Expand Down
Loading
Loading