chore: update ji local changes

offline-backend-20260512/backend/CLAUDE.md

@@ -166,7 +166,7 @@ Lead-agent middlewares are assembled in strict append order across `packages/har
 9. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
 10. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
 11. **TokenUsageMiddleware** - Records token usage metrics when token tracking is enabled (optional)
-12. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
+12. **TitleMiddleware** - Two-phase auto-title (never shows "untitled"): `before_model` sets an instant question-derived *provisional* title the moment the first user message arrives (no LLM, zero latency), then `after_model` asynchronously generates the final LLM title and replaces it (tracked via the `title_provisional` state flag). Normalizes structured message content before prompting the title model
 13. **MemoryMiddleware** - Memory V2: `wrap_model_call` injects Hindsight recall transiently; `after_agent` auto-retains the turn to Hindsight
 14. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
 15. **DeferredToolFilterMiddleware** - Hides deferred tool schemas from the bound model until tool search is enabled (optional)
@@ -178,7 +178,7 @@ Lead-agent middlewares are assembled in strict append order across `packages/har
 10. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
 11. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
 12. **TokenUsageMiddleware** - Records token usage metrics when token tracking is enabled (optional)
-13. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
+13. **TitleMiddleware** - Two-phase auto-title (never shows "untitled"): `before_model` sets an instant question-derived *provisional* title the moment the first user message arrives (no LLM, zero latency), then `after_model` asynchronously generates the final LLM title and replaces it (tracked via the `title_provisional` state flag). Normalizes structured message content before prompting the title model
 14. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
 15. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
 16. **DeferredToolFilterMiddleware** - Hides deferred tool schemas from the bound model until tool search is enabled (optional)