Two complementary changes to reduce conversation cold-start friction:
A. Returning-user re-greeting (backend)
- When WS reconnects to a non-empty conversation and last_message_at is older
than chat_re_greeting_idle_hours (default 6h), the agent emits a warm
continuation message that references prior history instead of staying silent.
- Self-debouncing: the AI message updates last_message_at, so reconnects
within the window will not re-trigger.
- Skipped while profile collection is still pending.
D. Topic suggestion chips (backend + Expo)
- New WS message type topic_suggestions carries 3-4 quick-start chips derived
from the current memoir stage's empty slots (deterministic, no extra LLM
cost). Sent alongside opening / re-greeting / resume.
- Expo chat screen renders a horizontally-scrollable chip row above the input
bar; tapping a chip sends the chip's text as a user message and clears the
row. Sending any text/voice also clears the chips.
Prefetch opening over WebSocket from the conversations list before navigation, with prepared-session handoff into the chat screen. Add a single-slot background pool so leaving chat (in-app) keeps the last session socket with UI callbacks stripped; dispose on app background and reconnect after resume when the chat screen is mounted. Tear down pooled sockets on logout, purge, and conversation delete. RealtimeSession supports attachUiCallbacks and idempotent dispose, and the chat composer hides the connection notice while connecting if assistant history already exists. Fix pause handler wiring in the conversation screen.
Co-authored-by: Cursor <cursoragent@cursor.com>
