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/client-api.ts

@@ -49,7 +49,7 @@ export class ApiError extends Error {
  * callback. Malformed lines are skipped (a half-written line must never break
  * the stream), and the trailing buffer is flushed at the end.
  */
-async function consumeNdjson(
+export async function consumeNdjson(
   response: Response,
   handleEvent: (event: unknown) => void,
 ): Promise<void> {
@@ -333,6 +333,12 @@ export type HealthModel = {
   note?: string;
 };
 
+export type HealthChatModel = {
+  name: string;
+  badge: "text" | "vision" | "both";
+  available: boolean | null;
+};
+
 export type Health = {
   ok: boolean;
   reachable: boolean;
@@ -344,6 +350,8 @@ export type Health = {
   hasApiKey: boolean;
   vision: HealthModel;
   text: HealthModel;
+  /** Chat model allowlist; optional so older servers/mocks stay valid. */
+  chatModels?: HealthChatModel[];
   latencyMs: number | null;
   modelCount: number | null;
   error: string | null;