Redesign dashboard: split Runtime Health and Hardware Summary

- Runtime Health now shows only LiveCD system status (services, tools,
  drivers, network, CUDA/ROCm) — hardware component rows removed
- Hardware Summary now shows server components with readable descriptions
  (model, count×size) and component-status.json health badges
- Add Network Adapters row to Hardware Summary
- SFP module static info (vendor, PN, SN, connector, type, wavelength)
  now collected via ethtool -m regardless of carrier state
- PSU statuses from IPMI audit written to component-status.json so PSU
  badge shows actual status after first audit instead of UNKNOWN

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-09 23:41:23 +03:00
parent c1690a084b
commit 05241f2e0e
7 changed files with 386 additions and 110 deletions

View File

@@ -1094,6 +1094,7 @@ func TestDashboardRendersRuntimeHealthTable(t *testing.T) {
}
body := rec.Body.String()
for _, needle := range []string{
// Runtime Health card — LiveCD checks only
`Runtime Health`,
`<th>Check</th><th>Status</th><th>Source</th><th>Issue</th>`,
`Export Directory`,
@@ -1102,16 +1103,18 @@ func TestDashboardRendersRuntimeHealthTable(t *testing.T) {
`CUDA / ROCm`,
`Required Utilities`,
`Bee Services`,
`<td>CPU</td>`,
`<td>Memory</td>`,
`<td>Storage</td>`,
`<td>GPU</td>`,
`CUDA runtime is not ready for GPU SAT.`,
`Missing: nvidia-smi`,
`bee-nvidia=inactive`,
`cpu SAT: FAILED`,
`storage SAT: FAILED`,
`sat:nvidia`,
// Hardware Summary card — component health badges
`Hardware Summary`,
`>CPU<`,
`>Memory<`,
`>Storage<`,
`>GPU<`,
`>PSU<`,
`badge-warn`, // cpu Warning badge
`badge-err`, // storage Critical badge
} {
if !strings.Contains(body, needle) {
t.Fatalf("dashboard missing %q: %s", needle, body)