Add per-model descriptions + repo-cleanup polish

- models.yaml: add 'description' field for all 5 models (generic, anyone-can-use)
- ModelDef gains optional description: str | None field
- UI: render description below meta tags; mute the repo line further
- escapeHtml() for safety in case descriptions/names contain HTML chars
- Update runbook: how to add a new model with description

image/app/models.py

@@ -12,6 +12,7 @@ class ModelDef(BaseModel):
     capabilities: list[str] = Field(default_factory=list)
     expected_ready_seconds: int = 300
     vllm_args: list[str] = Field(default_factory=list)
+    description: str | None = None
 
 
 class Defaults(BaseModel):

image/app/static/app.js

@@ -18,6 +18,16 @@ const state = {
 const el = (sel) => document.querySelector(sel);
 const $$ = (sel) => document.querySelectorAll(sel);
 
+function escapeHtml(s) {
+  if (s == null) return '';
+  return String(s)
+    .replaceAll('&', '&')
+    .replaceAll('<', '&lt;')
+    .replaceAll('>', '&gt;')
+    .replaceAll('"', '&quot;')
+    .replaceAll("'", '&#39;');
+}
+
 async function fetchJSON(url, opts) {
   const r = await fetch(url, opts);
   if (!r.ok) {
@@ -38,14 +48,18 @@ function renderCards() {
     const isActive = key === state.current_model_key;
     const card = document.createElement('div');
     card.className = 'card' + (isActive ? ' active' : '');
+    const desc = m.description
+      ? `<div class="desc">${escapeHtml(m.description)}</div>`
+      : '';
     card.innerHTML = `
-      <div class="name">${m.display_name}</div>
+      <div class="name">${escapeHtml(m.display_name)}</div>
       <div class="meta">
         <span class="tag mode-${m.mode}">${m.mode}</span>
         <span class="tag">${m.size_gb} GB</span>
-        ${(m.capabilities || []).map(c => `<span class="tag cap">${c}</span>`).join('')}
+        ${(m.capabilities || []).map(c => `<span class="tag cap">${escapeHtml(c)}</span>`).join('')}
       </div>
-      <div class="muted small repo">${m.repo}</div>
+      ${desc}
+      <div class="muted small repo">${escapeHtml(m.repo)}</div>
       <div class="spacer"></div>
       <button class="btn ${isActive ? '' : 'primary'}" data-key="${key}" ${isActive || isSwapping ? 'disabled' : ''}>
         ${isActive ? 'Current' : 'Switch to this'}

image/app/static/style.css

@@ -170,7 +170,16 @@ main {
 }
 .card .name { font-weight: 600; font-size: 15px; }
 .card .meta { display: flex; flex-wrap: wrap; gap: 6px; font-size: 12px; color: var(--muted); }
-.card .repo { word-break: break-all; }
+.card .desc {
+  font-size: 13.5px;
+  line-height: 1.5;
+  color: #b9b9c4;
+}
+.card .repo {
+  word-break: break-all;
+  font-size: 11px;
+  color: #5c5c66;
+}
 .tag {
   background: var(--surface-2);
   border: 1px solid var(--border);

image/models.yaml

@@ -15,6 +15,11 @@ defaults:
 models:
   qwen3-vl:
     display_name: "Qwen3-VL 235B (vision)"
+    description: >-
+      Qwen's flagship multimodal model. 235B total parameters with ~22B
+      active per token (Mixture-of-Experts). Handles text, images, and
+      many languages. The most capable model in this catalog — also the
+      slowest to load because it splits across both Sparks.
     repo: RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
     size_gb: 135
     mode: cluster
@@ -28,6 +33,10 @@ models:
 
   gemma4:
     display_name: "Gemma 4 31B"
+    description: >-
+      Google's mid-size reasoning model. 31B dense parameters with built-in
+      thinking mode and function-calling. Strong on math, logic, and
+      structured outputs; also supports vision input. Runs solo on one Spark.
     repo: RedHatAI/gemma-4-31B-it-NVFP4
     size_gb: 23
     mode: solo
@@ -45,6 +54,10 @@ models:
 
   qwen36:
     display_name: "Qwen3.6 35B-A3B (daily driver)"
+    description: >-
+      Qwen's latest fast Mixture-of-Experts model: 35B total parameters but
+      only ~3B active per token, making inference quick. Long 64K-token
+      context window. A good default for everyday chat and longer documents.
     repo: RedHatAI/Qwen3.6-35B-A3B-NVFP4
     size_gb: 20
     mode: solo
@@ -61,6 +74,10 @@ models:
 
   qwen3-235b-fp8:
     display_name: "Qwen3 235B-A22B FP8 (legacy)"
+    description: >-
+      Earlier generation of the Qwen 235B family in native FP8 precision.
+      Runs across both Sparks. Mostly superseded by Qwen3-VL above; keep
+      around for text-only baseline comparisons.
     repo: Qwen/Qwen3-235B-A22B-FP8
     size_gb: 220
     mode: cluster
@@ -74,6 +91,9 @@ models:
 
   qwen25-72b:
     display_name: "Qwen2.5 72B (legacy)"
+    description: >-
+      Last-generation 72B dense model. Cluster mode required due to size.
+      Kept for compatibility and baseline comparison against newer Qwens.
     repo: Qwen/Qwen2.5-72B-Instruct
     size_gb: 145
     mode: cluster

runbook.md

@@ -36,9 +36,11 @@ These take effect on the **next swap to that model**. If a swap fails after this
 
 ## Adding a new model
 
-1. Add an entry to `models.yaml` (in the image source) or, post-install, via the "Edit Model Catalog" action in StartOS.
+1. Add an entry to `image/models.yaml`. Required fields: `display_name`, `repo`, `size_gb`, `mode` (`solo` or `cluster`), `vllm_args`. Optional but recommended: `description` (one paragraph — what the model is, what it's good for, how it differs from others; renders below the meta tags in each card), `capabilities` (tags like `[vision, reasoning, tools]`), `expected_ready_seconds`.
 2. Confirm the weights are on the Spark: `ssh <spark-user>@<spark-1-host>.local 'ls ~/.cache/huggingface/hub/'`. If not, download with `./hf-download.sh <repo>` on Spark 1.
-3. The new model appears in the UI on next refresh.
+3. Rebuild + redeploy the package: `cd package && make x86 && make install`.
+
+If `description` is omitted, the card simply hides that section — no need to populate it for every model. Keep descriptions generic (not user-specific) so the catalog stays portable.
 
 ## Manual swap fallback