Add NVIDIA self-heal tools and per-GPU SAT status

audit/internal/app/sat_overlay_test.go

@@ -59,3 +59,51 @@ func TestApplyLatestSATStatusesMarksAMDGPUs(t *testing.T) {
 		t.Fatalf("gpu status=%v want Critical", snap.PCIeDevices[0].Status)
 	}
 }
+
+func TestApplyLatestSATStatusesMarksNvidiaGPUByPerGPUStatusFile(t *testing.T) {
+	baseDir := t.TempDir()
+	runDir := filepath.Join(baseDir, "gpu-nvidia-20260407-162123")
+	if err := os.MkdirAll(runDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(runDir, "summary.txt"), []byte("run_at_utc=2026-04-07T16:21:23Z\noverall_status=FAILED\n"), 0644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(runDir, "gpu-1-status.txt"), []byte("gpu_index=1\ngpu_name=NVIDIA H100 PCIe\nrun_status=FAILED\nreason=GPU requires reset\n"), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	class := "VideoController"
+	manufacturer := "NVIDIA Corporation"
+	bdf0 := "0000:4b:00.0"
+	bdf1 := "0000:4f:00.0"
+	snap := schema.HardwareSnapshot{
+		PCIeDevices: []schema.HardwarePCIeDevice{
+			{
+				DeviceClass:  &class,
+				Manufacturer: &manufacturer,
+				BDF:          &bdf0,
+				Telemetry:    map[string]any{"nvidia_gpu_index": 0},
+			},
+			{
+				DeviceClass:  &class,
+				Manufacturer: &manufacturer,
+				BDF:          &bdf1,
+				Telemetry:    map[string]any{"nvidia_gpu_index": 1},
+			},
+		},
+	}
+
+	applyLatestSATStatuses(&snap, baseDir, nil)
+
+	if snap.PCIeDevices[1].Status == nil || *snap.PCIeDevices[1].Status != "Critical" {
+		t.Fatalf("gpu1 status=%v want Critical", snap.PCIeDevices[1].Status)
+	}
+	if snap.PCIeDevices[1].ErrorDescription == nil || *snap.PCIeDevices[1].ErrorDescription != "GPU requires reset failed" {
+		got := "<nil>"
+		if snap.PCIeDevices[1].ErrorDescription != nil {
+			got = *snap.PCIeDevices[1].ErrorDescription
+		}
+		t.Fatalf("gpu1 error=%q want per-gpu reason", got)
+	}
+}