feat: draft settings persistence — shared model/thinking/context record for the new-session surfaces

Both new-session pages (the home graph view's topic dock and /chat/new)
held their model + thinking + knowledge-context choices in plain
useState(undefined) — every navigation reset them to config defaults.

Now both surfaces read/write ONE server-side record
(data/draft-settings.json via GET/PUT /api/settings/draft, the
render-settings pattern): whatever the learner last left the controls on
is what every later visit shows. useDraftSettings loads on mount with a
touch-guard (a slow GET never clobbers a fast choice), saves
optimistically. Session creation still carries the choice into the new
chat exactly as before; per-session settings are untouched.

The PUT validation is the exact per-chat contract — parseSettingsBody
extracted verbatim from app/api/chats/[id]/settings and shared by both
routes (unknown model/level → 400 with the supported list, never a
silent clamp). 400s on garbage, {} = the clear-overrides write.

Live-verified: Cmd+K+Enter model pick, Shift+Tab thinking cycle, context
slider — all held across home → session → home → /chat/new, and carried
into a created session's record.

config.ts

@@ -132,3 +132,11 @@ export const EMBEDDINGS_FILE = path.join(PATHS.graph, "embeddings.json");
  * read-modify-write. Shared shape/sanitizer: src/core/render-settings.ts.
  */
 export const RENDER_SETTINGS_FILE = path.join(PATHS.graph, "render-settings.json");
+
+/**
+ * DRAFT (pre-session) settings — the model + thinking + knowledge-context
+ * selections shared by the two new-session surfaces (the home graph view
+ * and /chat/new). One small JSON blob, read-modify-write, written only
+ * through the validated app/api/settings/draft route.
+ */
+export const DRAFT_SETTINGS_FILE = path.join(DATA_ROOT, "draft-settings.json");