homepage: capability equivalence on the AI cards

Every fleet model card (and the #models docs section) now states, in
plain family-facing terms, what the model is equivalent to:
frank-large ~ Claude Sonnet 5 / OpenAI-Luna, frank-primary ~ Claude
Opus 4.8 / OpenAI-Terra (both Summer 2026 frontier), frank-secondary ~
last year (2025) frontier. Rendered as a new details.equiv line
(desc-equiv, styled in the head color, bare-mode clean); pinned in
homepage_config.bats.

shared/homepage/docs.html

@@ -56,6 +56,7 @@
   <h2>frank-large — deep reasoning</h2>
   <ul>
     <li><strong>Model:</strong> Qwen3.8-Flash-Next v2 Swift1.5 abliterated (halogen flash-server, ~62&nbsp;GiB) — an uncensored edition that thinks before answering.</li>
+    <li><strong>Equivalent:</strong> Claude Sonnet 5 / OpenAI-Luna (Summer 2026 frontier intelligence).</li>
     <li><strong>Capacity:</strong> 200k-token context, two conversations at a time; sees images.</li>
     <li><strong>Inputs:</strong> text, image.</li>
     <li><strong>Best for:</strong> cybersecurity and debugging. <em>Use requires Frank's permission.</em></li>
@@ -64,6 +65,7 @@
   <h2>frank-primary — the primary model</h2>
   <ul>
     <li><strong>Model:</strong> Qwen3.8-Flash-Next at native FP8 precision (radiance, 173&nbsp;GiB across both R9700s) — the biggest brain on the network.</li>
+    <li><strong>Equivalent:</strong> Claude Opus 4.8 / OpenAI-Terra (Summer 2026 frontier intelligence).</li>
     <li><strong>Capacity:</strong> 200k-token context, two conversations at a time; sees images.</li>
     <li><strong>Inputs:</strong> text, image.</li>
     <li><strong>Best for:</strong> software engineering, system administration, and instruction tasks.</li>
@@ -72,6 +74,7 @@
   <h2>frank-secondary — the fast utility model</h2>
   <ul>
     <li><strong>Model:</strong> Qwen3.5-9B-Uncensored (Q6_K, 6.9&nbsp;GiB) on the RTX&nbsp;3090 — roughly 95 tokens per second.</li>
+    <li><strong>Equivalent:</strong> last year's frontier level (2025).</li>
     <li><strong>Capacity:</strong> two simultaneous conversations, 200k tokens each; sees images.</li>
     <li><strong>Inputs:</strong> text, image.</li>
     <li><strong>Best for:</strong> agentic search, RAG, research subagents, translation, roleplay, and summarization — any small task that doesn't need much intelligence, and anything with a picture (screenshots, photos, diagrams). This is the model Open&nbsp;WebUI offers to family accounts.</li>