feat: refactor product data retrieval - Fix URL parsing in description_text_full - Update system_prompt to require product_ids in responses - Remove graph singleton for hot reload support - Improve product enrichment logic

- Add reset_limit.py service for tracking daily reset usage via Redis
- Add archive_history method in conversation_manager.py to rename old messages
- Add POST /api/history/archive endpoint with limit check
- Update frontend with Reset button next to Send button
- Limit LLM context to 15 messages per session
- Filter chat history by current date (auto-clear next day)

- Add create_embeddings_async() to support OpenAI batch embedding API
- Refactor data_retrieval_tool to batch embed all queries in ONE request
- Replace print() with logger.info() in product_search_helpers
- Remove visual_search checks (only text search supported)

Performance: 5-10x faster for multi-search queries (300ms vs 1.5s for 5 queries)
Rate Limit: Saves RPM by batching multiple embeddings into single API call

- Dockerfile.dev: Development environment with hot reload & cache mount
- Add Makefile targets: build-dev, run-dev for easy local testing
- Hot reload watches agent, api, common directories
- Includes health check endpoint

Usage:
  make build-dev  # Build dev image
  make run-dev    # Run container with volume mount for hot reload

- Both Dockerfile.stage and Dockerfile.prod now use --mount=type=cache
- Faster builds with BuildKit cache mount (temporary, per-build)
- Requires: docker buildx or DOCKER_BUILDKIT=1

- Remove --no-cache-dir flag from pip install
- Use Docker layer caching for faster production builds
- Manual server rebuilds will auto-update packages if needed

- Package not compatible with Python 3.11
- Remove to fix Docker build

- StarRocksConnection: Use StarRocksConnectionManager singleton with lazy loading
- Langfuse: Implement LangfuseClientManager singleton with lazy loading
- EmbeddingService: Already using singleton pattern
- Remove context managers (Langfuse auto-traces LangChain)
- Fix imports across agent/tools and server
- Clean up unnecessary comments and fix code organization

- Removed OpenTelemetry (TracerProvider, OTLPSpanExporter, LoggingInstrumentor, FastAPIInstrumentor)
- Implemented Langfuse v3.11.0 with CallbackHandler for LLM tracing
- Added langfuse_trace_context() with propagate_attributes() for proper user_id filtering
- Fixed user_id to appear in Langfuse User ID filter (not just metadata)
- Added session_id and tags propagation for trace organization
- Updated controller.py to wrap graph execution in langfuse_trace_context
- Verified traces send to self-hosted Langfuse at http://172.16.2.207:3009
- Configuration: LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, LANGFUSE_BASE_URL in .env

GIAI_DOAN_1 COMPLETE: LLM observability via Langfuse SDK
Next: GIAI_DOAN_2 - Container monitoring stack (cAdvisor + Prometheus + Grafana)