homepage: rework LLM model cards to structured role/spec/use lines

Each LLM card now carries a details object (role/spec/use) rendered as a
bold pale-green role, a bright-green spec line, and a dim 'Use:' line.
app.js descHTML() falls back to the plain description for non-LLM cards;
new .desc-role/.desc-spec/.desc-use CSS + bare-mode reset.

Roles made neutral (no nicknames): frank-large = deep reasoning,
frank-medium = primary model, frank-small = fast utility model.

The /docs model guide was fixed — it had drifted to retired model info
(frank-large as Qwen3.8-Flash-Next 87.3 GiB/200k, frank-medium as FP8
~31 GiB) — now Qwen3.8-27B UD-Q8_K_XL 31.5 GiB/262k and MXFP4/W4A8
19.4 GiB, reordered large->medium->small. bats 30/30 + live render.

shared/homepage/services.json

@@ -267,7 +267,11 @@
     "name": "frank-large",
     "category": "user",
     "section": "AI",
-    "description": "Qwen3.8-27B (UD-Q8_K_XL, 31.5 GiB) — 262k-token context, one conversation at a time. The big brain: long, thoughtful text conversations, DFlash2 spec decode. Text only; it cannot see images. Suggested use: cybersecurity and debugging tasks — use requires Frank's permission.",
+    "details": {
+      "role": "Deep reasoning model",
+      "spec": "Qwen3.8-27B (UD-Q8_K_XL, 31.5 GiB) — 262k-token context, one conversation at a time, text only.",
+      "use": "Cybersecurity and debugging. Requires Frank's permission."
+    },
     "url": "",
     "docs": "/docs#models",
     "probe": "127.0.0.1:7770",
@@ -279,7 +283,11 @@
     "name": "frank-medium",
     "category": "user",
     "section": "AI",
-    "description": "Qwen3.8-27B-Uncensored (MXFP4/W4A8, 19.4 GiB) — 262k-token context shared by up to eight conversations. The primary intelligent model: surpasses Claude Sonnet 5 per Artificial Analysis. Suggested use: software engineering, system administration, and instruction tasks. It sees images.",
+    "details": {
+      "role": "Primary model",
+      "spec": "Qwen3.8-27B-Uncensored (MXFP4/W4A8, 19.4 GiB) — 262k-token context across up to eight conversations; sees images. Beats Claude Sonnet 5 per Artificial Analysis.",
+      "use": "Software engineering, system administration, and instruction tasks."
+    },
     "url": "",
     "docs": "/docs#models",
     "probe": "192.168.0.235:7770",
@@ -291,7 +299,11 @@
     "name": "frank-small",
     "category": "user",
     "section": "AI",
-    "description": "Gemma4-12B QAT (Q4_K_M, 7.4 GiB) — 1M-token pool across four 262k-token conversations. The fast, cheap utility model and the eyes (screenshots, photos, diagrams). Suggested use: agentic search, text/audio/image RAG, research subagents, language translation, roleplaying games, summarization — any small utility task that doesn't require much intelligence.",
+    "details": {
+      "role": "Fast utility model",
+      "spec": "Gemma4-12B QAT (Q4_K_M, 7.4 GiB) — 1M-token pool across four conversations; fastest at images.",
+      "use": "Agentic search, RAG, research subagents, translation, roleplay, and summarization — any small task that doesn't need much intelligence."
+    },
     "url": "",
     "docs": "/docs#models",
     "probe": "127.0.0.1:7771",