Explore/magellan serve

cmd/power.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"sync"
+	"time"
 
 	"github.com/OpenCHAMI/magellan/internal/format"
 	"github.com/OpenCHAMI/magellan/pkg/bmc"
@@ -14,12 +15,15 @@ import (
 	"github.com/rs/zerolog/log"
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
-	"github.com/stmcginnis/gofish/redfish"
+	"github.com/stmcginnis/gofish/schemas"
 )
 
 var (
 	list_reset_types bool
 	reset_type       string
+	operation        string
+	waitForConfirm   bool
+	waitTimeout      time.Duration
 	powerFormat      format.DataFormat = format.FORMAT_JSON
 )
 
@@ -29,18 +33,33 @@ var PowerCmd = &cobra.Command{
 	Use: "power <node-id>...",
 	Example: `  // get power state
   magellan power x1000c0s0b3n0
-  // perform a particular type of reset
+  // perform a vendor-neutral power operation (resolved to a supported reset type)
+  magellan power x1000c0s0b3n0 -o off
+  magellan power x1000c0s0b3n0 -o hard-restart
+  // perform a raw Redfish reset type (no validation/fallback)
   magellan power x1000c0s0b3n0 -r On
   magellan power x1000c0s0b3n0 -r PowerCycle
   // list supported reset types
-  magellan power x1000c0s0b3n0 -l
+  magellan power x1000c0s0b3n0 --list-reset-types
   // more realistic usage
   magellan power -u USER -p PASS -f collect.json x1000c0s0b3n0 x1000c0s0b3n1 x1000c0s0b3n2
   // inventory from stdin
   magellan collect -v ... | magellan power -f - x1000c0s0b3n0`,
 	Short: "Get and set node power states",
 	Long:  "Determine and control the power states of nodes found by a previous inventory crawl.\nSee the 'scan' and 'crawl' commands for further details.",
 	Run: func(cmd *cobra.Command, args []string) {
+		// Context for cancellation/deadlines, propagated into the BMC layer.
+		ctx := cmd.Context()
+
+		// Validate the requested operation up front so a bad value fails once,
+		// clearly, rather than once per target node.
+		if operation != "" && !bmc.KnownOperation(bmc.Operation(operation)) {
+			log.Fatal().Msgf("unknown power operation %q (known: %v)", operation, bmc.Operations())
+		}
+		if waitForConfirm && operation == "" {
+			log.Fatal().Msg("--wait requires --operation (raw --reset-type has no confirmable target)")
+		}
+
 		// Read node inventory from CLI flag, or default `collect` YAML output
 		var datafile string
 		if viper.IsSet("inventory-file") {
@@ -145,18 +164,51 @@ var PowerCmd = &cobra.Command{
 		var action_func func(power.CrawlableNode) string
 		if list_reset_types {
 			action_func = func(target power.CrawlableNode) string {
-				types, err := power.GetResetTypes(target)
+				types, err := power.GetResetTypes(ctx, target)
 				if err != nil {
 					log.Error().Err(err).Msgf("failed to get reset types for node %s", target.ClusterID)
 					return ""
 				}
 				return fmt.Sprintf("%s", types)
 			}
+		} else if operation != "" && waitForConfirm {
+			// Vendor-neutral operation, confirmed: issue, then poll to the target
+			// power state (escalating a timed-out graceful op to its forced
+			// equivalent) within the deadline.
+			op := bmc.Operation(operation)
+			opts := bmc.DefaultTransitionOptions()
+			opts.Timeout = waitTimeout
+			action_func = func(target power.CrawlableNode) string {
+				res, err := power.PowerTransition(ctx, target, op, opts)
+				if err != nil {
+					log.Error().Err(err).Msgf("failed to perform %q on node %s", operation, target.ClusterID)
+					return "failure"
+				}
+				msg := string(res.Status)
+				if res.FinalState != "" {
+					msg += fmt.Sprintf(" (%s)", res.FinalState)
+				}
+				if res.Escalated {
+					msg += fmt.Sprintf(" [escalated to %s]", res.EscalatedTo)
+				}
+				return msg
+			}
+		} else if operation != "" {
+			// Vendor-neutral operation: resolved to a supported reset type with
+			// the graceful→forced fallback chain in the BMC layer.
+			action_func = func(target power.CrawlableNode) string {
+				_, err := power.ResetOperation(ctx, target, bmc.Operation(operation))
+				if err != nil {
+					log.Error().Err(err).Msgf("failed to perform %q on node %s", operation, target.ClusterID)
+					return "failure"
+				}
+				return "success"
+			}
 		} else if reset_type != "" {
 			action_func = func(target power.CrawlableNode) string {
-				// TODO: Some kind of validation might be nice here, but ResetType
-				// is a custom string type, so a direct typecast works fine for now.
-				err := power.ResetComputerSystem(target, redfish.ResetType(reset_type))
+				// Raw Redfish reset type, passed through unresolved. Prefer
+				// --operation for vendor-neutral semantics with fallbacks.
+				_, err := power.ResetComputerSystem(ctx, target, schemas.ResetType(reset_type))
 				if err != nil {
 					log.Error().Err(err).Msgf("failed to reset node %s", target.ClusterID)
 					return "failure"
@@ -165,7 +217,7 @@ var PowerCmd = &cobra.Command{
 			}
 		} else {
 			action_func = func(target power.CrawlableNode) string {
-				state, err := power.GetPowerState(target)
+				state, err := power.GetPowerState(ctx, target)
 				if err != nil {
 					log.Error().Err(err).Msgf("failed to get power state of node %s", target.ClusterID)
 					state = "unknown"
@@ -236,10 +288,16 @@ func concurrent_helper(concurrency int, targets []power.CrawlableNode, runner fu
 }
 
 func init() {
-	// Alternative actions from the default power-state query
-	PowerCmd.Flags().BoolVarP(&list_reset_types, "list-reset-types", "l", false, "List supported Redfish reset types")
-	PowerCmd.Flags().StringVarP(&reset_type, "reset-type", "r", "", "Redfish reset type to perform")
-	PowerCmd.MarkFlagsMutuallyExclusive("reset-type", "list-reset-types")
+	// Alternative actions from the default power-state query.
+	// NOTE: no "-l" shorthand here — it is reserved globally for --log-level on
+	// the root command (cmd/root.go). Defining it again panics pflag at execution
+	// time when the persistent flags are merged into this subcommand's flagset.
+	PowerCmd.Flags().BoolVar(&list_reset_types, "list-reset-types", false, "List supported Redfish reset types")
+	PowerCmd.Flags().StringVarP(&reset_type, "reset-type", "r", "", "Raw Redfish reset type to perform (no validation/fallback; prefer --operation)")
+	PowerCmd.Flags().StringVarP(&operation, "operation", "o", "", "Vendor-neutral power operation (on|off|soft-off|force-off|soft-restart|hard-restart|init)")
+	PowerCmd.Flags().BoolVar(&waitForConfirm, "wait", false, "With --operation, wait until the target reaches its expected power state (escalating a timed-out graceful op)")
+	PowerCmd.Flags().DurationVar(&waitTimeout, "wait-timeout", bmc.DefaultTimeout, "Maximum time to wait for --wait confirmation")
+	PowerCmd.MarkFlagsMutuallyExclusive("reset-type", "list-reset-types", "operation")
 
 	// Normal config options
 	PowerCmd.Flags().StringP("inventory-file", "f", "", "YAML file containing node inventory")

cmd/power_test.go

@@ -0,0 +1,30 @@
+package cmd
+
+import (
+	"bytes"
+	"testing"
+)
+
+// TestPowerCommandExecutes guards against shorthand-flag collisions between the
+// power subcommand and the root command's persistent flags. pflag merges the
+// root persistent flags into a subcommand's flagset at execution time and
+// panics on a duplicate shorthand (e.g. the historical --list-reset-types/-l vs
+// --log-level/-l clash). Executing `power --help` forces that merge without
+// running the command body, so any reintroduced collision fails here instead of
+// at runtime for every user.
+func TestPowerCommandExecutes(t *testing.T) {
+	var out bytes.Buffer
+	rootCmd.SetOut(&out)
+	rootCmd.SetErr(&out)
+	rootCmd.SetArgs([]string{"power", "--help"})
+	t.Cleanup(func() { rootCmd.SetArgs(nil) })
+
+	// A shorthand collision surfaces as a panic during flag merge; the test
+	// fails (rather than the process aborting) if that regresses.
+	if err := rootCmd.Execute(); err != nil {
+		t.Fatalf("executing `power --help` returned an error: %v", err)
+	}
+	if out.Len() == 0 {
+		t.Fatal("expected help output for `power --help`, got none")
+	}
+}

cmd/root.go

@@ -196,4 +196,9 @@ func SetDefaults() {
 	viper.SetDefault("update.component", "")
 	viper.SetDefault("update.status", false)
 	viper.SetDefault("power.cacert", "")
+	viper.SetDefault("server.host", "")
+	viper.SetDefault("server.port", 8443)
+	viper.SetDefault("server.tls-cert", "")
+	viper.SetDefault("server.tls-key", "")
+	viper.SetDefault("server.auth-token", "")
 }

cmd/serve.go

@@ -0,0 +1,77 @@
+package cmd
+
+import (
+	"context"
+	"fmt"
+	"os/signal"
+	"syscall"
+
+	"github.com/OpenCHAMI/magellan/internal/server"
+	"github.com/OpenCHAMI/magellan/pkg/secrets"
+	"github.com/OpenCHAMI/magellan/pkg/service"
+	"github.com/rs/zerolog/log"
+	"github.com/spf13/cobra"
+	"github.com/spf13/viper"
+)
+
+var (
+	serveHost      string
+	servePort      int
+	serveTLSCert   string
+	serveTLSKey    string
+	serveAuthToken string
+)
+
+// ServeCmd runs magellan as a long-lived REST service over the shared BMC core,
+// so other OpenCHAMI tools can delegate discovery, inventory, and power
+// operations to magellan instead of talking to BMCs directly (RFD #133).
+var ServeCmd = &cobra.Command{
+	Use:   "serve",
+	Short: "Run magellan as a long-lived BMC service (REST API)",
+	Long: "Run magellan as a persistent daemon exposing a REST API for BMC inventory and\n" +
+		"power operations, backed by the same shared core the CLI uses. The server runs\n" +
+		"until it receives SIGINT or SIGTERM, then drains in-flight requests.",
+	Run: func(cmd *cobra.Command, args []string) {
+		// Resolve BMC credentials from the local secret store, matching the
+		// other subcommands. Per-request credentials are a later enhancement.
+		store, err := secrets.OpenStore(secretsFile)
+		if err != nil {
+			log.Warn().Err(err).Str("path", secretsFile).Msg("failed to open secrets store; BMC operations will fail until credentials are available")
+		}
+
+		svc := service.New(store)
+		svc.Insecure = insecure
+		defer svc.Close()
+
+		srv := server.New(svc, server.Config{
+			Addr:      fmt.Sprintf("%s:%d", serveHost, servePort),
+			TLSCert:   serveTLSCert,
+			TLSKey:    serveTLSKey,
+			AuthToken: serveAuthToken,
+		})
+
+		// Cancel the run context on SIGINT/SIGTERM to trigger graceful shutdown.
+		ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
+		defer stop()
+
+		if err := srv.ListenAndServe(ctx); err != nil {
+			log.Fatal().Err(err).Msg("magellan daemon error")
+		}
+		log.Info().Msg("magellan daemon stopped")
+	},
+}
+
+func init() {
+	ServeCmd.Flags().StringVar(&serveHost, "host", "", "Host/IP to bind (default: all interfaces)")
+	ServeCmd.Flags().IntVar(&servePort, "port", 8443, "Port to listen on")
+	ServeCmd.Flags().StringVar(&serveTLSCert, "tls-cert", "", "Path to TLS certificate (enables HTTPS when set with --tls-key)")
+	ServeCmd.Flags().StringVar(&serveTLSKey, "tls-key", "", "Path to TLS private key")
+	ServeCmd.Flags().StringVar(&serveAuthToken, "auth-token", "", "Require this bearer token on /v1 routes (auth disabled when empty)")
+	ServeCmd.Flags().StringVar(&secretsFile, "secrets-file", "", "Path to the node secrets file")
+	ServeCmd.Flags().BoolVarP(&insecure, "insecure", "i", false, "Ignore BMC TLS verification errors")
+
+	checkBindFlagError(viper.BindPFlag("server.host", ServeCmd.Flags().Lookup("host")))
+	checkBindFlagError(viper.BindPFlag("server.port", ServeCmd.Flags().Lookup("port")))
+
+	rootCmd.AddCommand(ServeCmd)
+}

go.mod

@@ -1,65 +1,56 @@
 module github.com/OpenCHAMI/magellan
 
-go 1.23
-
-toolchain go1.24.5
+go 1.26.0
 
 require (
 	github.com/cznic/mathutil v0.0.0-20181122101859-297441e03548
-	github.com/go-chi/chi/v5 v5.1.0
+	github.com/go-chi/chi/v5 v5.3.0
 	github.com/jmoiron/sqlx v1.4.0
-	github.com/lestrrat-go/jwx v1.2.29
-	github.com/mattn/go-sqlite3 v1.14.22
+	github.com/lestrrat-go/jwx v1.2.31
+	github.com/mattn/go-sqlite3 v1.14.45
 	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c
-	github.com/spf13/cobra v1.8.1
-	github.com/spf13/viper v1.19.0
-	github.com/stmcginnis/gofish v0.19.0
-	golang.org/x/exp v0.0.0-20240409090435-93d18d7e34b8
+	github.com/spf13/cobra v1.10.2
+	github.com/spf13/viper v1.21.0
+	github.com/stmcginnis/gofish v0.22.0
+	golang.org/x/exp v0.0.0-20260611194520-c48552f49976
 )
 
 require (
 	github.com/Cray-HPE/hms-xname v1.4.0
-	github.com/rs/zerolog v1.33.0
-	github.com/stretchr/testify v1.9.0
-	golang.org/x/crypto v0.32.0
+	github.com/rs/zerolog v1.35.1
+	github.com/stretchr/testify v1.11.1
+	golang.org/x/crypto v0.53.0
 	gopkg.in/yaml.v3 v3.0.1
 )
 
 require (
-	github.com/google/go-cmp v0.6.0 // indirect
-	github.com/mattn/go-colorable v0.1.13 // indirect
-	github.com/mattn/go-isatty v0.0.20 // indirect
+	github.com/mattn/go-colorable v0.1.15 // indirect
+	github.com/mattn/go-isatty v0.0.22 // indirect
 )
 
 require (
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
-	github.com/decred/dcrd/dcrec/secp256k1/v4 v4.2.0 // indirect
-	github.com/fsnotify/fsnotify v1.7.0 // indirect
-	github.com/goccy/go-json v0.10.2 // indirect
-	github.com/hashicorp/hcl v1.0.0 // indirect
+	github.com/decred/dcrd/dcrec/secp256k1/v4 v4.4.1 // indirect
+	github.com/fsnotify/fsnotify v1.10.1 // indirect
+	github.com/go-viper/mapstructure/v2 v2.5.0 // indirect
+	github.com/goccy/go-json v0.10.6 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/lestrrat-go/backoff/v2 v2.0.8 // indirect
-	github.com/lestrrat-go/blackmagic v1.0.2 // indirect
+	github.com/lestrrat-go/blackmagic v1.0.4 // indirect
 	github.com/lestrrat-go/httpcc v1.0.1 // indirect
 	github.com/lestrrat-go/iter v1.0.2 // indirect
 	github.com/lestrrat-go/option v1.0.1 // indirect
-	github.com/magiconair/properties v1.8.7 // indirect
-	github.com/mitchellh/mapstructure v1.5.0 // indirect
-	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
+	github.com/pelletier/go-toml/v2 v2.3.1 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
-	github.com/sagikazarmark/locafero v0.4.0 // indirect
-	github.com/sagikazarmark/slog-shim v0.1.0 // indirect
-	github.com/sourcegraph/conc v0.3.0 // indirect
-	github.com/spf13/afero v1.11.0 // indirect
-	github.com/spf13/cast v1.6.0 // indirect
-	github.com/spf13/pflag v1.0.5 // indirect
+	github.com/sagikazarmark/locafero v0.12.0 // indirect
+	github.com/spf13/afero v1.15.0 // indirect
+	github.com/spf13/cast v1.10.0 // indirect
+	github.com/spf13/pflag v1.0.10 // indirect
 	github.com/subosito/gotenv v1.6.0 // indirect
-	go.uber.org/atomic v1.9.0 // indirect
-	go.uber.org/multierr v1.9.0 // indirect
-	golang.org/x/sys v0.29.0 // indirect
-	golang.org/x/text v0.21.0 // indirect
+	go.yaml.in/yaml/v3 v3.0.4 // indirect
+	golang.org/x/sys v0.46.0 // indirect
+	golang.org/x/text v0.38.0 // indirect
 	gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect
-	gopkg.in/ini.v1 v1.67.0 // indirect
 )