Fix AMD GPU false detection, blackbox deadlock, and NOGPU build bloat

- sat.go: DetectGPUVendor lspci fallback now checks GPU device classes
  ([0300]/[0302]/[0380]) per line instead of scanning the whole output for
  vendor name; AMD EPYC servers have dozens of AMD-branded PCIe entries
  (Root Complex, IOMMU, Host Bridge) that were triggering the old check
- blackbox.go: fix deadlock in finishCycle — it held w.mu while calling
  persistState(), which acquires rt.mu then re-acquires w.mu inside
  persistStateLocked(); now w.mu is released before persistState()
- build.sh: remove NVIDIA-specific overlay files (bee-gpu-burn,
  bee-john-gpu-stress, bee-nccl-gpu-stress, bee-nvidia-recover,
  bee-dcgmproftester-staggered, bee-check-nvswitch,
  nvidia-fabricmanager.service.d/) for non-nvidia build variants
- bee-selfheal: gate NVIDIA recovery on BEE_GPU_VENDOR=nvidia so the
  script does not attempt to restart bee-nvidia.service on NOGPU builds

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

audit/internal/app/blackbox.go

@@ -365,7 +365,6 @@ func (w *blackboxWorker) currentFlushPeriod() time.Duration {
 
 func (w *blackboxWorker) finishCycle(duration time.Duration, err error) {
 	w.mu.Lock()
-	defer w.mu.Unlock()
 	w.lastDuration = duration
 	if err != nil {
 		w.status = "degraded"
@@ -383,6 +382,10 @@ func (w *blackboxWorker) finishCycle(duration time.Duration, err error) {
 		}
 		w.flushPeriod = adjustFlushPeriod(w.flushPeriod, duration, true, w.fastCycles)
 	}
+	w.mu.Unlock()
+	// persistState must be called without w.mu held: it acquires rt.mu then
+	// each worker.mu inside persistStateLocked, so holding w.mu here would
+	// cause a deadlock (w.mu → rt.mu → w.mu).
 	w.runtime.persistState()
 }
 

audit/internal/platform/sat.go

@@ -182,11 +182,18 @@ func (s *System) DetectGPUVendor() string {
 		return "amd"
 	}
 	if raw, err := exec.Command("lspci", "-nn").Output(); err == nil {
-		text := strings.ToLower(string(raw))
+		// Only match AMD GPU device classes [0300]=VGA, [0302]=3D controller, [0380]=Display.
-		if strings.Contains(text, "advanced micro devices") || strings.Contains(text, "amd/ati") {
+		// AMD CPUs also appear in lspci as "Advanced Micro Devices" (Root Complex, IOMMU, etc.)
+		// so matching vendor alone causes false positives on AMD CPU servers without GPUs.
+		for _, line := range strings.Split(strings.ToLower(string(raw)), "\n") {
+			if !strings.Contains(line, "advanced micro devices") && !strings.Contains(line, "amd/ati") {
+				continue
+			}
+			if strings.Contains(line, "[0300]") || strings.Contains(line, "[0302]") || strings.Contains(line, "[0380]") {
 				return "amd"
 			}
 		}
+	}
 	return ""
 }
 

iso/builder/build.sh

@@ -1419,6 +1419,13 @@ rm -rf \
 if [ "$BEE_GPU_VENDOR" != "nvidia" ]; then
     rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-nvidia-load"
     rm -f "${OVERLAY_STAGE_DIR}/etc/systemd/system/bee-nvidia.service"
+    rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-gpu-burn"
+    rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-john-gpu-stress"
+    rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-nccl-gpu-stress"
+    rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-nvidia-recover"
+    rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-dcgmproftester-staggered"
+    rm -f "${OVERLAY_STAGE_DIR}/usr/local/bin/bee-check-nvswitch"
+    rm -rf "${OVERLAY_STAGE_DIR}/etc/systemd/system/nvidia-fabricmanager.service.d"
 fi
 
 # --- inject authorized_keys for SSH access ---

iso/overlay/usr/local/bin/bee-selfheal

@@ -67,7 +67,8 @@ if ! mkdir "${LOCK_DIR}" 2>/dev/null; then
 fi
 trap 'rmdir "${LOCK_DIR}" >/dev/null 2>&1 || true' EXIT
 
-if have_nvidia_gpu && [ ! -e /dev/nvidia0 ]; then
+GPU_VENDOR=$(cat /etc/bee-gpu-vendor 2>/dev/null || echo "")
+if [ "$GPU_VENDOR" = "nvidia" ] && have_nvidia_gpu && [ ! -e /dev/nvidia0 ]; then
     log_event "NVIDIA GPU detected but /dev/nvidia0 is missing"
     restart_service bee-nvidia.service || true
 fi