Fix GPU model propagation, export filenames, PSU/service status, and chart perf

- nvidia.go: add Name field to nvidiaGPUInfo, include model name in
  nvidia-smi query, set dev.Model in enrichPCIeWithNVIDIAData
- pages.go: fix duplicate GPU count in validate card summary (4 GPU: 4 x …
  → 4 x … GPU); fix PSU UNKNOWN fallback from hw.PowerSupplies; treat
  activating/deactivating/reloading service states as OK in Runtime Health
- support_bundle.go: use "150405" time format (no colons) for exFAT compat
- sat.go / benchmark.go / platform_stress.go / sat_fan_stress.go: remove
  .tar.gz archive creation from export dirs — export packs everything itself
- charts_svg.go: add min-max downsampling (1400 pt cap) for SVG chart perf
- benchmark_report.go / sat.go: normalize GPU fallback to "Unknown GPU"

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

audit/internal/app/support_bundle.go

@@ -213,7 +213,7 @@ func BuildSupportBundle(exportDir string) (string, error) {
 
 	now := time.Now().UTC()
 	date := now.Format("2006-01-02")
-	tod := now.Format("15:04:05")
+	tod := now.Format("150405")
 	ver := bundleVersion()
 	model := serverModelForBundle()
 	sn := serverSerialForBundle()

audit/internal/platform/benchmark.go

@@ -335,11 +335,7 @@ func (s *System) RunNvidiaBenchmark(ctx context.Context, baseDir string, opts Nv
 		return "", fmt.Errorf("write summary.txt: %w", err)
 	}
 
-	archive := filepath.Join(baseDir, "gpu-benchmark-"+ts+".tar.gz")
-	if err := createTarGz(archive, runDir); err != nil {
-		return "", fmt.Errorf("pack benchmark archive: %w", err)
-	}
-	return archive, nil
+	return runDir, nil
 }
 
 func normalizeNvidiaBenchmarkOptionsForBenchmark(opts NvidiaBenchmarkOptions) NvidiaBenchmarkOptions {

audit/internal/platform/benchmark_report.go

@@ -90,7 +90,7 @@ func renderBenchmarkReportWithCharts(result NvidiaBenchmarkResult, charts []benc
 	for _, gpu := range result.GPUs {
 		name := strings.TrimSpace(gpu.Name)
 		if name == "" {
-			name = "Unknown"
+			name = "Unknown GPU"
 		}
 		interconnect := "-"
 		if gpu.Scores.InterconnectScore > 0 {

audit/internal/platform/platform_stress.go

@@ -161,13 +161,7 @@ func (s *System) RunPlatformStress(
 	}
 	_ = os.WriteFile(filepath.Join(runDir, "summary.txt"), []byte(summary), 0644)
 
-	// Pack tar.gz
-	archivePath := filepath.Join(baseDir, "platform-stress-"+stamp+".tar.gz")
-	if err := packPlatformDir(runDir, archivePath); err != nil {
-		return "", fmt.Errorf("pack archive: %w", err)
-	}
-	_ = os.RemoveAll(runDir)
-	return archivePath, nil
+	return runDir, nil
 }
 
 // collectPhase samples live metrics every second until ctx is done.

audit/internal/platform/sat.go

@@ -662,11 +662,7 @@ func (s *System) RunStorageAcceptancePack(ctx context.Context, baseDir string, e
 	if err := os.WriteFile(filepath.Join(runDir, "summary.txt"), []byte(summary.String()), 0644); err != nil {
 		return "", err
 	}
-	archive := filepath.Join(baseDir, "storage-"+ts+".tar.gz")
-	if err := createTarGz(archive, runDir); err != nil {
-		return "", err
-	}
-	return archive, nil
+	return runDir, nil
 }
 
 type satJob struct {
@@ -852,11 +848,7 @@ func runAcceptancePackCtx(ctx context.Context, baseDir, prefix string, jobs []sa
 		}
 	}
 
-	archive := filepath.Join(baseDir, prefix+"-"+ts+".tar.gz")
-	if err := createTarGz(archive, runDir); err != nil {
-		return "", err
-	}
-	return archive, nil
+	return runDir, nil
 }
 
 func updateNvidiaGPUStatus(perGPU map[int]*nvidiaGPUStatusFile, idx int, status, jobName, detail string) {
@@ -919,7 +911,7 @@ func writeNvidiaGPUStatusFiles(runDir, overall string, perGPU map[int]*nvidiaGPU
 			entry.Health = "UNKNOWN"
 		}
 		if entry.Name == "" {
-			entry.Name = "unknown"
+			entry.Name = "Unknown GPU"
 		}
 		var body strings.Builder
 		fmt.Fprintf(&body, "gpu_index=%d\n", entry.Index)

audit/internal/platform/sat_fan_stress.go

@@ -223,11 +223,7 @@ func (s *System) RunFanStressTest(ctx context.Context, baseDir string, opts FanS
 		return "", err
 	}
 
-	archive := filepath.Join(baseDir, "fan-stress-"+ts+".tar.gz")
-	if err := createTarGz(archive, runDir); err != nil {
-		return "", err
-	}
-	return archive, nil
+	return runDir, nil
 }
 
 func applyFanStressDefaults(opts *FanStressOptions) {

audit/internal/webui/charts_svg.go

@@ -83,6 +83,10 @@ func renderMetricChartSVG(title string, labels []string, times []time.Time, data
 		}
 	}
 
+	// Downsample to at most ~1400 points (one per pixel) before building SVG.
+	times, datasets = downsampleTimeSeries(times, datasets, 1400)
+	pointCount = len(times)
+
 	statsLabel := chartStatsLabel(datasets)
 
 	legendItems := []metricChartSeries{}
@@ -196,6 +200,19 @@ func drawGPUOverviewChartSVG(title string, labels []string, times []time.Time, s
 		}
 	}
 
+	// Downsample to at most ~1400 points before building SVG.
+	{
+		datasets := make([][]float64, len(series))
+		for i := range series {
+			datasets[i] = series[i].Values
+		}
+		times, datasets = downsampleTimeSeries(times, datasets, 1400)
+		pointCount = len(times)
+		for i := range series {
+			series[i].Values = datasets[i]
+		}
+	}
+
 	scales := make([]chartScale, len(series))
 	for i := range series {
 		min, max := chartSeriesBounds(series[i].Values)
@@ -626,6 +643,87 @@ func writeTimelineBoundaries(b *strings.Builder, layout chartLayout, start, end
 	b.WriteString(`</g>` + "\n")
 }
 
+// downsampleTimeSeries reduces the time series to at most maxPts points using
+// min-max bucketing. Each bucket contributes the index of its min and max value
+// (using the first full-length dataset as the reference series). All parallel
+// datasets are sampled at those same indices so all series stay aligned.
+// If len(times) <= maxPts the inputs are returned unchanged.
+func downsampleTimeSeries(times []time.Time, datasets [][]float64, maxPts int) ([]time.Time, [][]float64) {
+	n := len(times)
+	if n <= maxPts || maxPts <= 0 {
+		return times, datasets
+	}
+	buckets := maxPts / 2
+	if buckets < 1 {
+		buckets = 1
+	}
+	// Use the first dataset that has the same length as times as the reference
+	// for deciding which two indices to keep per bucket.
+	var ref []float64
+	for _, ds := range datasets {
+		if len(ds) == n {
+			ref = ds
+			break
+		}
+	}
+	selected := make([]int, 0, maxPts)
+	bucketSize := float64(n) / float64(buckets)
+	for b := 0; b < buckets; b++ {
+		lo := int(math.Round(float64(b) * bucketSize))
+		hi := int(math.Round(float64(b+1) * bucketSize))
+		if hi > n {
+			hi = n
+		}
+		if lo >= hi {
+			continue
+		}
+		if ref == nil {
+			selected = append(selected, lo)
+			if hi-1 != lo {
+				selected = append(selected, hi-1)
+			}
+			continue
+		}
+		minIdx, maxIdx := lo, lo
+		for i := lo + 1; i < hi; i++ {
+			if ref[i] < ref[minIdx] {
+				minIdx = i
+			}
+			if ref[i] > ref[maxIdx] {
+				maxIdx = i
+			}
+		}
+		if minIdx <= maxIdx {
+			selected = append(selected, minIdx)
+			if maxIdx != minIdx {
+				selected = append(selected, maxIdx)
+			}
+		} else {
+			selected = append(selected, maxIdx)
+			if minIdx != maxIdx {
+				selected = append(selected, minIdx)
+			}
+		}
+	}
+	outTimes := make([]time.Time, len(selected))
+	for i, idx := range selected {
+		outTimes[i] = times[idx]
+	}
+	outDatasets := make([][]float64, len(datasets))
+	for d, ds := range datasets {
+		if len(ds) != n {
+			outDatasets[d] = ds
+			continue
+		}
+		out := make([]float64, len(selected))
+		for i, idx := range selected {
+			out[i] = ds[idx]
+		}
+		outDatasets[d] = out
+	}
+	return outTimes, outDatasets
+}
+
 func chartXForTime(ts, start, end time.Time, left, right int) float64 {
 	if !end.After(start) {
 		return float64(left+right) / 2

audit/internal/webui/pages.go

@@ -349,6 +349,9 @@ func renderHardwareSummaryCard(opts HandlerOptions) string {
 	writeRow("GPU", hwDescribeGPU(hw), runtimeStatusBadge(gpuRow.Status))
 
 	psuRow := aggregateComponentStatus("PSU", records, nil, []string{"psu:"})
+	if psuRow.Status == "UNKNOWN" && len(hw.PowerSupplies) > 0 {
+		psuRow.Status = hwPSUStatus(hw.PowerSupplies)
+	}
 	writeRow("PSU", hwDescribePSU(hw), runtimeStatusBadge(psuRow.Status))
 
 	if nicDesc := hwDescribeNIC(hw); nicDesc != "" {
@@ -506,6 +509,31 @@ func hwDescribeGPU(hw schema.HardwareSnapshot) string {
 	return strings.Join(parts, ", ")
 }
 
+// hwPSUStatus returns "OK", "CRITICAL", "WARNING", or "UNKNOWN" based on
+// PSU statuses from the audit snapshot. Used as fallback when component-status.json
+// has no psu: records yet (e.g. first boot before audit writes them).
+func hwPSUStatus(psus []schema.HardwarePowerSupply) string {
+	worst := "UNKNOWN"
+	for _, psu := range psus {
+		if psu.Status == nil {
+			continue
+		}
+		switch strings.ToUpper(strings.TrimSpace(*psu.Status)) {
+		case "CRITICAL":
+			return "CRITICAL"
+		case "WARNING":
+			if worst != "CRITICAL" {
+				worst = "WARNING"
+			}
+		case "OK":
+			if worst == "UNKNOWN" {
+				worst = "OK"
+			}
+		}
+	}
+	return worst
+}
+
 // hwDescribePSU returns a summary like "2× 1600 W" or "2× PSU".
 func hwDescribePSU(hw schema.HardwareSnapshot) string {
 	n := len(hw.PowerSupplies)
@@ -742,7 +770,13 @@ func buildRuntimeServicesRow(health schema.RuntimeHealth) runtimeHealthRow {
 	nonActive := make([]string, 0)
 	for _, svc := range health.Services {
 		state := strings.TrimSpace(strings.ToLower(svc.Status))
-		if state != "active" {
+		// "activating" and "deactivating" are transient states for oneshot services
+		// (RemainAfterExit=yes) — the service is running normally, not failed.
+		// Only "failed" and "inactive" (after services should be running) are problems.
+		switch state {
+		case "active", "activating", "deactivating", "reloading":
+			// OK — service is running or transitioning normally
+		default:
 			nonActive = append(nonActive, svc.Name+"="+svc.Status)
 		}
 	}
@@ -1777,6 +1811,11 @@ func formatValidateDeviceSummary(total int, models map[string]int, unit string)
 	if total != 1 {
 		label += "s"
 	}
+	// If there is only one model the leading count duplicates the per-model
+	// count already in parts (e.g. "4 GPU: 4 x RTX …" → "4 x RTX …").
+	if len(parts) == 1 {
+		return parts[0] + " " + label
+	}
 	return fmt.Sprintf("%d %s: %s", total, label, strings.Join(parts, ", "))
 }