Add HLD/LLD architecture page and clarify agent-framework vs story-tree branching

Adds docs/architecture.html (a standalone walkthrough of the context
budget, world-state engine, story tree, egress fix, and pen-test
findings) and links it from the landing page. Also clarifies in
GUIDE.md §1.8 that "no branching" describes per-turn control flow,
not the story tree's branching data.

docs/GUIDE.md

@@ -541,6 +541,13 @@ narrate, then a separate structured-extraction step, with a retry branch when ex
 fails and a tool-calling path for dice — that is a graph, and hand-rolling it would get
 ugly fast.
 
+**This is not the same branching as the story tree (§2.2).** "No branching" here
+describes *control flow*: the code path a single turn takes through the backend. That path
+never forks. It is not true of the *data* the app stores. When a player rewinds and plays a
+turn differently, that action creates a new branch in the saved history. One turn's
+execution is a straight line. The sequence of turns across a playthrough is a tree. The two
+claims are about different things and do not conflict.
+
 ---
 
 # Part 2 — Data and correctness

docs/index.html

@@ -131,6 +131,7 @@
     <div class="cta">
       <a class="btn btn-primary" href="https://ai-dnd-1gmp.onrender.com">Launch the live demo →</a>
       <a class="btn btn-ghost" href="guide.html">Read the design notes</a>
+      <a class="btn btn-ghost" href="architecture.html">HLD &amp; LLD walkthrough</a>
       <a class="btn btn-ghost" href="https://github.com/parththakkar106/AI-DnD">View the source</a>
     </div>
     <p class="wake">No sign-up, no API key. Hosted on a free tier that sleeps — the first load takes ~30–60s to wake.</p>