1. Verbose live progress during SAT tests (CPU, Memory, Storage, AMD GPU)

- New tui/sat_progress.go: polls {DefaultSATBaseDir}/{prefix}-*/verbose.log every 300ms and parses completed/in-progress steps - Busy screen now shows each step as PASS lscpu (234ms) / FAIL stress-ng (60.0s) / ... sensors-after instead of just "Working..." 2. Test results shown on screen (instead of just "Archive written to /path") - RunCPUAcceptancePackResult, RunMemoryAcceptancePackResult, RunStorageAcceptancePackResult, RunAMDAcceptancePackResult now read summary.txt from the run directory and return a formatted per-step result: Run: 2025-03-25T10:00:00Z PASS lscpu PASS sensors-before FAIL stress-ng PASS sensors-after Overall: FAILED (ok=3 failed=1) 3. AMD GPU SAT with auto-detection - platform.System.DetectGPUVendor(): checks /dev/nvidia0 → "nvidia", /dev/kfd → "amd" - platform.System.RunAMDAcceptancePack(): runs rocm-smi, rocm-smi --showallinfo, dmidecode - GPU SAT (G key / GPU row enter) automatically routes to AMD or NVIDIA based on detected vendor - "Run All" also auto-detects vendor 4. Panel detail view - GPU detail now shows the most recent (NVIDIA or AMD) SAT result, whichever is newer - All SAT detail views use the same human-readable formatSATDetail format
2026-03-25 17:54:27 +03:00
parent adcc147b32
commit 0c16616cc9
9 changed files with 300 additions and 57 deletions
--- a/audit/internal/app/app.go
+++ b/audit/internal/app/app.go
@@ -77,6 +77,9 @@ type satRunner interface {
 	RunStorageAcceptancePack(baseDir string) (string, error)
 	RunCPUAcceptancePack(baseDir string, durationSec int) (string, error)
 	ListNvidiaGPUs() ([]platform.NvidiaGPU, error)
+	DetectGPUVendor() string
+	ListAMDGPUs() ([]platform.AMDGPUInfo, error)
+	RunAMDAcceptancePack(baseDir string) (string, error)
 }

 type runtimeChecker interface {
@@ -431,11 +434,7 @@ func (a *App) RunMemoryAcceptancePack(baseDir string) (string, error) {

 func (a *App) RunMemoryAcceptancePackResult(baseDir string) (ActionResult, error) {
 	path, err := a.RunMemoryAcceptancePack(baseDir)
-	body := "Archive written."
-	if path != "" {
-		body = "Archive written to " + path
-	}
-	return ActionResult{Title: "Memory SAT", Body: body}, err
+	return ActionResult{Title: "Memory SAT", Body: satResultBody(path)}, err
 }

 func (a *App) RunCPUAcceptancePack(baseDir string, durationSec int) (string, error) {
@@ -447,11 +446,7 @@ func (a *App) RunCPUAcceptancePack(baseDir string, durationSec int) (string, err

 func (a *App) RunCPUAcceptancePackResult(baseDir string, durationSec int) (ActionResult, error) {
 	path, err := a.RunCPUAcceptancePack(baseDir, durationSec)
-	body := "Archive written."
-	if path != "" {
-		body = "Archive written to " + path
-	}
-	return ActionResult{Title: "CPU SAT", Body: body}, err
+	return ActionResult{Title: "CPU SAT", Body: satResultBody(path)}, err
 }

 func (a *App) RunStorageAcceptancePack(baseDir string) (string, error) {
@@ -463,11 +458,41 @@ func (a *App) RunStorageAcceptancePack(baseDir string) (string, error) {

 func (a *App) RunStorageAcceptancePackResult(baseDir string) (ActionResult, error) {
 	path, err := a.RunStorageAcceptancePack(baseDir)
-	body := "Archive written."
-	if path != "" {
-		body = "Archive written to " + path
+	return ActionResult{Title: "Storage SAT", Body: satResultBody(path)}, err
+}
+
+func (a *App) DetectGPUVendor() string {
+	return a.sat.DetectGPUVendor()
+}
+
+func (a *App) ListAMDGPUs() ([]platform.AMDGPUInfo, error) {
+	return a.sat.ListAMDGPUs()
+}
+
+func (a *App) RunAMDAcceptancePack(baseDir string) (string, error) {
+	if strings.TrimSpace(baseDir) == "" {
+		baseDir = DefaultSATBaseDir
 	}
-	return ActionResult{Title: "Storage SAT", Body: body}, err
+	return a.sat.RunAMDAcceptancePack(baseDir)
+}
+
+func (a *App) RunAMDAcceptancePackResult(baseDir string) (ActionResult, error) {
+	path, err := a.RunAMDAcceptancePack(baseDir)
+	return ActionResult{Title: "AMD GPU SAT", Body: satResultBody(path)}, err
+}
+
+// satResultBody reads summary.txt from the SAT run directory (archive path without .tar.gz)
+// and returns a formatted human-readable result. Falls back to a plain message if unreadable.
+func satResultBody(archivePath string) string {
+	if archivePath == "" {
+		return "No output produced."
+	}
+	runDir := strings.TrimSuffix(archivePath, ".tar.gz")
+	raw, err := os.ReadFile(filepath.Join(runDir, "summary.txt"))
+	if err != nil {
+		return "Archive written to " + archivePath
+	}
+	return formatSATDetail(strings.TrimSpace(string(raw)))
 }

 func (a *App) HealthSummaryResult() ActionResult {
--- a/audit/internal/app/app_test.go
+++ b/audit/internal/app/app_test.go
@@ -130,6 +130,12 @@ func (f fakeSAT) RunCPUAcceptancePack(baseDir string, durationSec int) (string,
 	return "", nil
 }

+func (f fakeSAT) DetectGPUVendor() string { return "" }
+
+func (f fakeSAT) ListAMDGPUs() ([]platform.AMDGPUInfo, error) { return nil, nil }
+
+func (f fakeSAT) RunAMDAcceptancePack(baseDir string) (string, error) { return "", nil }
+
 func TestNetworkStatusFormatsInterfacesAndRoute(t *testing.T) {
 	t.Parallel()

@@ -380,10 +386,10 @@ func TestActionResultsUseFallbackBody(t *testing.T) {
 	if got, _ := a.RunNvidiaAcceptancePackResult(""); got.Body != "Archive written." {
 		t.Fatalf("sat body=%q", got.Body)
 	}
-	if got, _ := a.RunMemoryAcceptancePackResult(""); got.Body != "Archive written." {
+	if got, _ := a.RunMemoryAcceptancePackResult(""); got.Body != "No output produced." {
 		t.Fatalf("memory sat body=%q", got.Body)
 	}
-	if got, _ := a.RunStorageAcceptancePackResult(""); got.Body != "Archive written." {
+	if got, _ := a.RunStorageAcceptancePackResult(""); got.Body != "No output produced." {
 		t.Fatalf("storage sat body=%q", got.Body)
 	}
 }
--- a/audit/internal/app/panel.go
+++ b/audit/internal/app/panel.go
@@ -103,6 +103,22 @@ func (a *App) ComponentDetailResult(key string) ActionResult {
 	case "MEM":
 		return a.satDetailResult("memory", "memory-", "MEM detail")
 	case "GPU":
+		// Prefer whichever GPU SAT was run most recently.
+		nv, _ := filepath.Glob(filepath.Join(DefaultSATBaseDir, "gpu-nvidia-*/summary.txt"))
+		am, _ := filepath.Glob(filepath.Join(DefaultSATBaseDir, "gpu-amd-*/summary.txt"))
+		sort.Strings(nv)
+		sort.Strings(am)
+		latestNV := ""
+		if len(nv) > 0 {
+			latestNV = nv[len(nv)-1]
+		}
+		latestAM := ""
+		if len(am) > 0 {
+			latestAM = am[len(am)-1]
+		}
+		if latestAM > latestNV {
+			return a.satDetailResult("gpu", "gpu-amd-", "GPU detail")
+		}
 		return a.satDetailResult("gpu", "gpu-nvidia-", "GPU detail")
 	case "DISK":
 		return a.satDetailResult("storage", "storage-", "DISK detail")
@@ -190,7 +206,70 @@ func (a *App) satDetailResult(statusKey, prefix, title string) ActionResult {
 	if err != nil {
 		return ActionResult{Title: title, Body: "Could not read test results."}
 	}
-	return ActionResult{Title: title, Body: strings.TrimSpace(string(raw))}
+	return ActionResult{Title: title, Body: formatSATDetail(strings.TrimSpace(string(raw)))}
+}
+
+// formatSATDetail converts raw summary.txt key=value content to a human-readable per-step display.
+func formatSATDetail(raw string) string {
+	var b strings.Builder
+	kv := parseKeyValueSummary(raw)
+
+	if t, ok := kv["run_at_utc"]; ok {
+		fmt.Fprintf(&b, "Run: %s\n\n", t)
+	}
+
+	// Collect step names in order they appear in the file
+	lines := strings.Split(raw, "\n")
+	var stepKeys []string
+	seenStep := map[string]bool{}
+	for _, line := range lines {
+		if idx := strings.Index(line, "_status="); idx >= 0 {
+			key := line[:idx]
+			if !seenStep[key] && key != "overall" {
+				seenStep[key] = true
+				stepKeys = append(stepKeys, key)
+			}
+		}
+	}
+
+	for _, key := range stepKeys {
+		status := kv[key+"_status"]
+		display := cleanSummaryKey(key)
+		switch status {
+		case "OK":
+			fmt.Fprintf(&b, "PASS  %s\n", display)
+		case "FAILED":
+			fmt.Fprintf(&b, "FAIL  %s\n", display)
+		case "UNSUPPORTED":
+			fmt.Fprintf(&b, "SKIP  %s\n", display)
+		default:
+			fmt.Fprintf(&b, "?     %s\n", display)
+		}
+	}
+
+	if overall, ok := kv["overall_status"]; ok {
+		ok2 := kv["job_ok"]
+		failed := kv["job_failed"]
+		fmt.Fprintf(&b, "\nOverall: %s  (ok=%s  failed=%s)", overall, ok2, failed)
+	}
+
+	return strings.TrimSpace(b.String())
+}
+
+// cleanSummaryKey strips the leading numeric prefix from a SAT step key.
+// "1-lscpu" → "lscpu", "3-stress-ng" → "stress-ng"
+func cleanSummaryKey(key string) string {
+	idx := strings.Index(key, "-")
+	if idx <= 0 {
+		return key
+	}
+	prefix := key[:idx]
+	for _, c := range prefix {
+		if c < '0' || c > '9' {
+			return key
+		}
+	}
+	return key[idx+1:]
 }

 func (a *App) psuDetailResult() ActionResult {
@@ -247,6 +326,7 @@ func satStatuses() map[string]string {
 		prefix string
 	}{
 		{"gpu", "gpu-nvidia-"},
+		{"gpu", "gpu-amd-"},
 		{"memory", "memory-"},
 		{"storage", "storage-"},
 		{"cpu", "cpu-"},
--- a/audit/internal/platform/sat.go
+++ b/audit/internal/platform/sat.go
@@ -22,6 +22,56 @@ type NvidiaGPU struct {
 	MemoryMB int
 }

+// AMDGPUInfo holds basic info about an AMD GPU from rocm-smi.
+type AMDGPUInfo struct {
+	Index int
+	Name  string
+}
+
+// DetectGPUVendor returns "nvidia" if /dev/nvidia0 exists, "amd" if /dev/kfd exists, or "" otherwise.
+func (s *System) DetectGPUVendor() string {
+	if _, err := os.Stat("/dev/nvidia0"); err == nil {
+		return "nvidia"
+	}
+	if _, err := os.Stat("/dev/kfd"); err == nil {
+		return "amd"
+	}
+	return ""
+}
+
+// ListAMDGPUs returns AMD GPUs visible to rocm-smi.
+func (s *System) ListAMDGPUs() ([]AMDGPUInfo, error) {
+	out, err := exec.Command("rocm-smi", "--showproductname", "--csv").Output()
+	if err != nil {
+		return nil, fmt.Errorf("rocm-smi: %w", err)
+	}
+	var gpus []AMDGPUInfo
+	for _, line := range strings.Split(strings.TrimSpace(string(out)), "\n") {
+		line = strings.TrimSpace(line)
+		if line == "" || strings.HasPrefix(strings.ToLower(line), "device") {
+			continue
+		}
+		parts := strings.SplitN(line, ",", 2)
+		name := ""
+		if len(parts) >= 2 {
+			name = strings.TrimSpace(parts[1])
+		}
+		idx := len(gpus)
+		gpus = append(gpus, AMDGPUInfo{Index: idx, Name: name})
+	}
+	return gpus, nil
+}
+
+// RunAMDAcceptancePack runs an AMD GPU diagnostic pack using rocm-smi.
+func (s *System) RunAMDAcceptancePack(baseDir string) (string, error) {
+	return runAcceptancePack(baseDir, "gpu-amd", []satJob{
+		{name: "01-rocm-smi.log", cmd: []string{"rocm-smi"}},
+		{name: "02-rocm-smi-showallinfo.log", cmd: []string{"rocm-smi", "--showallinfo"}},
+		{name: "03-dmidecode-baseboard.log", cmd: []string{"dmidecode", "-t", "baseboard"}},
+		{name: "04-dmidecode-system.log", cmd: []string{"dmidecode", "-t", "system"}},
+	})
+}
+
 // ListNvidiaGPUs returns GPUs visible to nvidia-smi.
 func (s *System) ListNvidiaGPUs() ([]NvidiaGPU, error) {
 	out, err := exec.Command("nvidia-smi",
--- a/audit/internal/tui/forms.go
+++ b/audit/internal/tui/forms.go
@@ -1,6 +1,10 @@
 package tui

-import tea "github.com/charmbracelet/bubbletea"
+import (
+	"time"
+
+	tea "github.com/charmbracelet/bubbletea"
+)

 func (m model) updateStaticForm(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
 	switch msg.String() {
@@ -82,23 +86,57 @@ func (m model) updateConfirm(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
 			return m.executeRunAll()
 		case actionRunMemorySAT:
 			m.busyTitle = "Memory test"
-			return m, func() tea.Msg {
-				result, err := m.app.RunMemoryAcceptancePackResult("")
-				return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
-			}
+			m.progressPrefix = "memory"
+			m.progressSince = time.Now()
+			m.progressLines = nil
+			since := m.progressSince
+			return m, tea.Batch(
+				func() tea.Msg {
+					result, err := m.app.RunMemoryAcceptancePackResult("")
+					return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
+				},
+				pollSATProgress("memory", since),
+			)
 		case actionRunStorageSAT:
 			m.busyTitle = "Storage test"
-			return m, func() tea.Msg {
-				result, err := m.app.RunStorageAcceptancePackResult("")
-				return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
-			}
+			m.progressPrefix = "storage"
+			m.progressSince = time.Now()
+			m.progressLines = nil
+			since := m.progressSince
+			return m, tea.Batch(
+				func() tea.Msg {
+					result, err := m.app.RunStorageAcceptancePackResult("")
+					return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
+				},
+				pollSATProgress("storage", since),
+			)
 		case actionRunCPUSAT:
 			m.busyTitle = "CPU test"
+			m.progressPrefix = "cpu"
+			m.progressSince = time.Now()
+			m.progressLines = nil
+			since := m.progressSince
 			durationSec := hcCPUDurations[m.hcMode]
-			return m, func() tea.Msg {
-				result, err := m.app.RunCPUAcceptancePackResult("", durationSec)
-				return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
-			}
+			return m, tea.Batch(
+				func() tea.Msg {
+					result, err := m.app.RunCPUAcceptancePackResult("", durationSec)
+					return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
+				},
+				pollSATProgress("cpu", since),
+			)
+		case actionRunAMDGPUSAT:
+			m.busyTitle = "AMD GPU test"
+			m.progressPrefix = "gpu-amd"
+			m.progressSince = time.Now()
+			m.progressLines = nil
+			since := m.progressSince
+			return m, tea.Batch(
+				func() tea.Msg {
+					result, err := m.app.RunAMDAcceptancePackResult("")
+					return resultMsg{title: result.Title, body: result.Body, err: err, back: screenHealthCheck}
+				},
+				pollSATProgress("gpu-amd", since),
+			)
 		}
 	case "ctrl+c":
 		return m, tea.Quit
@@ -110,7 +148,7 @@ func (m model) confirmCancelTarget() screen {
 	switch m.pendingAction {
 	case actionExportBundle:
 		return screenExportTargets
-	case actionRunAll, actionRunMemorySAT, actionRunStorageSAT, actionRunCPUSAT:
+	case actionRunAll, actionRunMemorySAT, actionRunStorageSAT, actionRunCPUSAT, actionRunAMDGPUSAT:
 		return screenHealthCheck
 	default:
 		return screenMain
--- a/audit/internal/tui/screen_health_check.go
+++ b/audit/internal/tui/screen_health_check.go
@@ -116,6 +116,12 @@ func (m model) updateHealthCheck(msg tea.KeyMsg) (tea.Model, tea.Cmd) {
 func (m model) hcRunSingle(idx int) (tea.Model, tea.Cmd) {
 	switch idx {
 	case hcGPU:
+		if m.app.DetectGPUVendor() == "amd" {
+			m.pendingAction = actionRunAMDGPUSAT
+			m.screen = screenConfirm
+			m.cursor = 0
+			return m, nil
+		}
 		m.nvidiaDurIdx = m.hcMode
 		return m.enterNvidiaSATSetup()
 	case hcMemory:
@@ -159,27 +165,37 @@ func (m model) executeRunAll() (tea.Model, tea.Cmd) {
 	return m, func() tea.Msg {
 		var parts []string
 		if sel[hcGPU] {
-			gpus, err := app.ListNvidiaGPUs()
-			if err != nil || len(gpus) == 0 {
-				parts = append(parts, "=== GPU ===\nNo NVIDIA GPUs detected or driver not loaded.")
-			} else {
-				var indices []int
-				sizeMB := 0
-				for _, g := range gpus {
-					indices = append(indices, g.Index)
-					if sizeMB == 0 || g.MemoryMB < sizeMB {
-						sizeMB = g.MemoryMB
-					}
-				}
-				if sizeMB == 0 {
-					sizeMB = 64
-				}
-				r, err := app.RunNvidiaAcceptancePackWithOptions(context.Background(), "", durationSec, sizeMB, indices)
+			vendor := app.DetectGPUVendor()
+			if vendor == "amd" {
+				r, err := app.RunAMDAcceptancePackResult("")
 				body := r.Body
 				if err != nil {
 					body += "\nERROR: " + err.Error()
 				}
-				parts = append(parts, "=== GPU ===\n"+body)
+				parts = append(parts, "=== GPU (AMD) ===\n"+body)
+			} else {
+				gpus, err := app.ListNvidiaGPUs()
+				if err != nil || len(gpus) == 0 {
+					parts = append(parts, "=== GPU ===\nNo NVIDIA GPUs detected or driver not loaded.")
+				} else {
+					var indices []int
+					sizeMB := 0
+					for _, g := range gpus {
+						indices = append(indices, g.Index)
+						if sizeMB == 0 || g.MemoryMB < sizeMB {
+							sizeMB = g.MemoryMB
+						}
+					}
+					if sizeMB == 0 {
+						sizeMB = 64
+					}
+					r, err := app.RunNvidiaAcceptancePackWithOptions(context.Background(), "", durationSec, sizeMB, indices)
+					body := r.Body
+					if err != nil {
+						body += "\nERROR: " + err.Error()
+					}
+					parts = append(parts, "=== GPU ===\n"+body)
+				}
 			}
 		}
 		if sel[hcMemory] {
@@ -225,7 +241,7 @@ func renderHealthCheck(m model) string {

 	type comp struct{ name, desc, key string }
 	comps := []comp{
-		{"GPU", "nvidia-smi + bee-gpu-stress", "G"},
+		{"GPU", "nvidia/amd auto-detect", "G"},
 		{"MEMORY", "memtester", "M"},
 		{"STORAGE", "smartctl + NVMe self-test", "S"},
 		{"CPU", "audit diagnostics", "C"},
--- a/audit/internal/tui/types.go
+++ b/audit/internal/tui/types.go
@@ -2,6 +2,7 @@ package tui

 import (
 	"strings"
+	"time"

 	"bee/audit/internal/app"
 	"bee/audit/internal/platform"
@@ -31,14 +32,15 @@ const (
 type actionKind string

 const (
-	actionNone          actionKind = ""
-	actionDHCPOne       actionKind = "dhcp_one"
-	actionStaticIPv4    actionKind = "static_ipv4"
-	actionExportBundle  actionKind = "export_bundle"
-	actionRunAll        actionKind = "run_all"
-	actionRunMemorySAT  actionKind = "run_memory_sat"
-	actionRunStorageSAT actionKind = "run_storage_sat"
-	actionRunCPUSAT     actionKind = "run_cpu_sat"
+	actionNone             actionKind = ""
+	actionDHCPOne          actionKind = "dhcp_one"
+	actionStaticIPv4       actionKind = "static_ipv4"
+	actionExportBundle     actionKind = "export_bundle"
+	actionRunAll           actionKind = "run_all"
+	actionRunMemorySAT     actionKind = "run_memory_sat"
+	actionRunStorageSAT    actionKind = "run_storage_sat"
+	actionRunCPUSAT        actionKind = "run_cpu_sat"
+	actionRunAMDGPUSAT     actionKind = "run_amd_gpu_sat"
 )

 type model struct {
@@ -88,6 +90,11 @@ type model struct {
 	// NVIDIA SAT running
 	nvidiaSATCancel  func()
 	nvidiaSATAborted bool
+
+	// SAT verbose progress (CPU / Memory / Storage / AMD GPU)
+	progressLines  []string
+	progressPrefix string
+	progressSince  time.Time
 }

 type formField struct {
@@ -177,6 +184,8 @@ func (m model) confirmBody() (string, string) {
 	case actionRunCPUSAT:
 		modes := []string{"Quick (60s)", "Standard (300s)", "Express (900s)"}
 		return "CPU test", "Run stress-ng? Mode: " + modes[m.hcMode]
+	case actionRunAMDGPUSAT:
+		return "AMD GPU test", "Run AMD GPU diagnostic pack (rocm-smi)?"
 	default:
 		return "Confirm", "Proceed?"
 	}
--- a/audit/internal/tui/update.go
+++ b/audit/internal/tui/update.go
@@ -17,9 +17,19 @@ func (m model) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 			return m, nil
 		}
 		return m.updateKey(msg)
+	case satProgressMsg:
+		if m.busy && m.progressPrefix != "" {
+			if len(msg.lines) > 0 {
+				m.progressLines = msg.lines
+			}
+			return m, pollSATProgress(m.progressPrefix, m.progressSince)
+		}
+		return m, nil
 	case resultMsg:
 		m.busy = false
 		m.busyTitle = ""
+		m.progressLines = nil
+		m.progressPrefix = ""
 		m.title = msg.title
 		if msg.err != nil {
 			body := strings.TrimSpace(msg.body)
--- a/audit/internal/tui/view.go
+++ b/audit/internal/tui/view.go
@@ -39,6 +39,15 @@ func (m model) View() string {
 		if m.busyTitle != "" {
 			title = m.busyTitle
 		}
+		if len(m.progressLines) > 0 {
+			var b strings.Builder
+			fmt.Fprintf(&b, "%s\n\n", title)
+			for _, l := range m.progressLines {
+				fmt.Fprintf(&b, "  %s\n", l)
+			}
+			b.WriteString("\n[ctrl+c] quit\n")
+			return b.String()
+		}
 		return fmt.Sprintf("%s\n\nWorking...\n\n[ctrl+c] quit\n", title)
 	}
 	switch m.screen {