homepage: add per-model input modalities to the LLM cards

Each LLM card now lists its accepted inputs as a line (Inputs: text · image ·
audio), sourced from the harness models.yml:
- frank-large: text (no vision projector)
- frank-medium: text, image (Gemma4 vision path)
- frank-small: text, image, audio (Gemma4 projector audio encoder; audio is
  not in models.yml's input list only because OMP's schema rejects it, but the
  endpoint accepts input_audio parts)

New .desc-inputs CSS + bare-mode reset; /docs model guide gains an Inputs line
per model. bats 30/30 + live render verified.

shared/homepage/app.js

@@ -35,10 +35,11 @@ function esc(s) {
 // them (the LLM cards), else the plain description string.
 function descHTML(svc) {
     const d = svc.details;
-    if (d && (d.role || d.spec || d.use)) {
+    if (d && (d.role || d.spec || d.inputs || d.use)) {
         const lines = [];
         if (d.role) lines.push('<div class="desc-role">' + esc(d.role) + '</div>');
         if (d.spec) lines.push('<div class="desc-spec">' + esc(d.spec) + '</div>');
+        if (d.inputs && d.inputs.length) lines.push('<div class="desc-inputs">Inputs: ' + esc(d.inputs.join(' · ')) + '</div>');
         if (d.use) lines.push('<div class="desc-use">Use: ' + esc(d.use) + '</div>');
         return lines.join('');
     }