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.

lib/chat-trim.ts

@@ -0,0 +1,30 @@
+/**
+ * Pure helpers shared by the chat route (server) and the chat UI (client):
+ * token budgeting and the sliding history window. No directive, no deps, so
+ * both sides can import it.
+ */
+
+/** Rough token estimate (≈4 chars per token) — good enough for budgeting. */
+export function estimateTokens(text: string): number {
+  return Math.ceil(text.length / 4);
+}
+
+/** How much conversation history the sliding window keeps (≈6k tokens). */
+export const HISTORY_TOKEN_BUDGET = 6000;
+
+/** Keeps the most recent turns that fit the budget (sliding window). */
+export function trimHistory<T extends { role: "user" | "assistant"; content: string }>(
+  messages: T[],
+  budget = HISTORY_TOKEN_BUDGET,
+): T[] {
+  const kept: T[] = [];
+  let used = 0;
+  for (let index = messages.length - 1; index >= 0; index -= 1) {
+    const message = messages[index];
+    const cost = estimateTokens(message.content);
+    if (kept.length > 0 && used + cost > budget) break;
+    kept.unshift(message);
+    used += cost;
+  }
+  return kept;
+}