feat: integrate invite API and improve notification handling

- Add invite code display and binding functionality via API
- Fix notification unread count sync on auth state change
- Improve notification mark read with server state validation
- Add auth state listener to trigger notification refresh
- Add YaoCoinConverter for coin-to-yao type conversion
- Remove YaoLegend from divination screens (UI cleanup)
- Abbreviate relation labels in yao detail view
- Add re-register notice to account delete screen
- Update 'coins' terminology to 'points' in localization
- Fix backend points consumption to only run in CHAT mode
- Add HttpxAuthNoiseFilter to suppress auth endpoint logging
- Fix notification static_schema import path
- Add test coverage for notification bloc error handling
- Update AGENTS.md page header rules and image handling
- Delete deprecated run-dev.sh script

AGENTS.md

@@ -44,39 +44,8 @@ When viewing data in the database, use `supabase mcp` tools (`supabase_execute_s
 
 ## Image Handling
 
-When reading images, use `understand_image` tool instead of `Read` tool, especially when the model supports multimodal capabilities. Only use `Read` tool for non-image files.
+When reading images, check whether the model has native multimodal capability first. If it does, use `Read` tool to read images directly. If it does not, fall back to `understand_image` tool. Only use `Read` tool for non-image files.
 
-## Mobile Automation
-
-Use Midscene Skills for mobile UI automation.
-
-### When to trigger
-If the user asks to open app, navigate pages, tap, input text, scroll, verify UI, reproduce bug, or run mobile tests → treat as executable automation, not just explanation.
-
-### Platform
-- iOS → use Midscene iOS (requires WebDriverAgent at http://localhost:8100/status)
-- Android → use Midscene Android (requires `adb devices` available)
-
-If platform not specified:
-- Use current project platform if obvious
-- Otherwise ask
-
-### Preconditions
-- iOS: WDA must be ready
-- Android: device/emulator must be connected
-
-If not ready → stop and report missing requirement
-
-### Execution
-- Perform actual UI actions via Midscene Skills
-- Do not only describe test plan
-- Capture result (screen state / success / failure step)
-
-### Output
-Return:
-- success or failure
-- first failing step (if any)
-- key observation
 <!-- TRELLIS:START -->
 # Trellis Instructions