Ilker ManapandClaude Opus 5.5
7245dbe1dd
Issue #3 asked for commands to stop and start the system, and 05aa21c gave
only one machine's services. Now:
- llmgw stop sets serving.stopped in the cluster's settings, live: the
reconciler wants every model at no replicas, freeing every GPU, and the
gateway answers every POST under /v1/ with 503 system_stopped. The control
planes, agents and mirror keep running, and no model's definition changes.
- llmgw start clears it; every model is placed again as it asks.
- llmgw restart has every agent restart over its stream (RestartAgent), then
the other control planes over ssh, standbys before a leader, then this
one; engines keep serving.
- llmgw status is the cluster's summary, saying when it is stopped.
One machine's services moved to llmgw service status|start|stop|restart.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
74 lines
1.8 KiB
Go
74 lines
1.8 KiB
Go
// Package cli builds llmgw's command line surface.
|
|
package cli
|
|
|
|
import (
|
|
"log/slog"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/obs"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/version"
|
|
)
|
|
|
|
type globalFlags struct {
|
|
logLevel string
|
|
logFormat string
|
|
}
|
|
|
|
var global globalFlags
|
|
|
|
// Root returns the root command with all subcommands attached.
|
|
func Root() *cobra.Command {
|
|
root := &cobra.Command{
|
|
Use: "llmgw",
|
|
Short: "LLM gateway for multi-fabric InfiniBand and heterogeneous GPU clusters",
|
|
Long: "llmgw serves LLMs running on your own GPU servers behind a single\n" +
|
|
"OpenAI-compatible endpoint. One binary, different roles per subcommand.",
|
|
Version: version.Version,
|
|
SilenceUsage: true,
|
|
SilenceErrors: true,
|
|
PersistentPreRun: func(_ *cobra.Command, _ []string) {
|
|
obs.Setup(obs.Options{Level: global.logLevel, Format: global.logFormat})
|
|
},
|
|
// Bare, in a terminal: the setup screens or the console. Otherwise
|
|
// the help, as before.
|
|
RunE: func(cmd *cobra.Command, _ []string) error {
|
|
if interactive(cmd) {
|
|
return runHome(cmd)
|
|
}
|
|
return cmd.Help()
|
|
},
|
|
}
|
|
|
|
pf := root.PersistentFlags()
|
|
pf.StringVar(&global.logLevel, "log-level", "info", "log level: debug|info|warn|error")
|
|
pf.StringVar(&global.logFormat, "log-format", "text", "log format: text|json")
|
|
|
|
root.AddCommand(
|
|
newServerCmd(),
|
|
newAgentCmd(),
|
|
newCtlCmd(),
|
|
newTenancyCmd(),
|
|
newUsersCmd(),
|
|
newOrgCmd(),
|
|
newMirrorCmd(),
|
|
newBundleCmd(),
|
|
newSimEngineCmd(),
|
|
newDoctorCmd(),
|
|
newNodeCmd(),
|
|
newSelfUpgradeCmd(),
|
|
newReleaseCmd(),
|
|
newJoinCmd(),
|
|
newFirewallCmd(),
|
|
newWipeCmd(),
|
|
newDocsCmd(),
|
|
)
|
|
// status, start, stop and restart: the whole system; service: this
|
|
// machine's services.
|
|
root.AddCommand(newSystemCmds()...)
|
|
root.AddCommand(newServiceCmd())
|
|
return root
|
|
}
|
|
|
|
func logger() *slog.Logger { return slog.Default() }
|