Update PRD, plan, and agent instructions

docs/plan.md

@@ -84,6 +84,7 @@ The goal is to deliver an end-to-end, voice-first AI speaking coach that support
   - `UploadDocument` / `DocumentChunk` – files and parsed chunks with `vector` embeddings (stored alongside or extending the existing backend package under `app/backend`).
   - `ProgressSnapshot` – aggregate metrics for dashboards (per user and optionally per program).
   - `Subscription` / `PaymentEvent` – billing state and usage limits.
+  - **Note:** Seed the database with the specific plans defined in `README.md` (First Light, Spark, Glow, Shine, Radiance) and their respective limits.
 - Add related Alembic migrations; verify they run cleanly on dev DB.
 
 **Deliverables**
@@ -129,6 +130,8 @@ The goal is to deliver an end-to-end, voice-first AI speaking coach that support
   - Respect retention settings.
 - Implement post-session summarization endpoint / background job:
   - Generate per-session summary, strengths/weaknesses, recommended next steps.
+- Implement on-demand translation:
+  - Endpoint (e.g., `/chat/translate`) or integrated socket message to translate user/AI text between target and native languages (supporting PRD Section 4.2).
 
 **Deliverables**
 
@@ -248,6 +251,7 @@ The goal is to deliver an end-to-end, voice-first AI speaking coach that support
 - Build `ChatInterface.tsx`:
   - Microphone controls, connection status, basic waveform/level visualization.
   - Rendering of AI and user turns with text and visual aids (images, tables) as provided by backend/agent.
+  - **Translation Support:** UI controls to translate specific messages on demand (toggle or click-to-translate).
   - Error states for mic and network issues; text-only fallback UI.
 - Integrate with backend session APIs:
   - On login, call `GET /sessions/default`, then `POST /sessions/default/token`.