Chat mode, phase 1: grounded streaming chat over your notes

Entry points (no sixth tab): Ask in the Library header (desktop button,
phone icon), Ask about this deck in the deck menu, Ask a question on
study/homework results (compact result travels as context), and a Chat
row in the desktop sidebar. Phones get a full-screen route with back +
New chat; the tab bar steps aside.

- Client-side retrieval: chunk scoped decks (~800 tokens), BM25 against
  the question + recent turns, top chunks under ~7k tokens, each
  labelled with deck + section. Notes come from the deck's stored
  sourceText (already kept for Regenerate); decks without it fall back
  to generated content and the UI says so.
- Stateless server: /api/chat validates against the CHAT_MODELS
  allowlist, trims the history to ~6k tokens, caps context at ~9k and
  streams token/thinking/done/error NDJSON. /api/chat/extract reduces
  attachments to text through the existing vision step.
- UI: user bubbles + full-width assistant text, streaming with stop,
  auto-scroll that pauses with a jump-to-bottom button, safe markdown
  (React nodes, no HTML injection; KaTeX dynamically imported only when
  a message has math), Thinking row for reasoning, copy/regenerate/
  edit-and-resend, model + context pickers (last model remembered),
  composer with visualViewport keyboard handling, safe-area, 16px
  textarea, Enter-to-send on desktop.
- Usage-limit failures keep the draft and show the shared message with
  Settings/Ollama actions; stopping maps the reader abort to a clean
  stopped state; offline disables sending with a reason.
- Settings: Keep notes text for chat toggle; deck menu: Delete notes
  text. RATE_LIMIT_CHAT + CHAT_MODELS in .env.example and README.
- Tests: chat suite (63 checks, stub Ollama) wired into run-all.
  Full set: 12/12 suites, 487 checks. SW -> freezmo-v32.

Also: tests/model-compare.mjs (diagnostic) benchmarks two models on the
same notes (latency, repair rounds, activity types) so the gpt-oss vs
gemma default can be decided on numbers; defaults unchanged.

components/chat/MathSpan.tsx

@@ -0,0 +1,41 @@
+"use client";
+
+import { useEffect, useRef } from "react";
+
+/**
+ * Math rendering, loaded only when a message actually contains math: KaTeX is
+ * imported dynamically (its CSS with it) the first time a span mounts and
+ * writes into this span imperatively — no HTML injection anywhere.
+ */
+export function MathSpan({ tex, display = false }: { tex: string; display?: boolean }) {
+  const ref = useRef<HTMLSpanElement>(null);
+
+  useEffect(() => {
+    let cancelled = false;
+    void (async () => {
+      try {
+        const [katex] = await Promise.all([import("katex"), import("katex/dist/katex.min.css")]);
+        if (cancelled || !ref.current) return;
+        katex.default.render(tex, ref.current, {
+          displayMode: display,
+          throwOnError: false,
+          strict: false,
+          trust: false,
+        });
+      } catch {
+        if (!cancelled && ref.current) ref.current.textContent = tex;
+      }
+    })();
+    return () => {
+      cancelled = true;
+    };
+  }, [tex, display]);
+
+  return (
+    <span
+      ref={ref}
+      className={display ? "my-2 block overflow-x-auto text-center" : "inline-block max-w-full align-middle"}
+      aria-label={tex}
+    />
+  );
+}