Initial commit: Vera-AI v2 with async Qdrant, singleton pattern, monthly curation, and configurable UID/GID/TZ

Features:
- AsyncQdrantClient for non-blocking Qdrant operations
- Singleton pattern for QdrantService
- Monthly full curation (day 1 at 03:00)
- Configurable UID/GID for Docker
- Timezone support via TZ env var
- Configurable log directory (VERA_LOG_DIR)
- Volume mounts for config/, prompts/, logs/
- Standard Docker format with .env file

Fixes:
- Removed unused system_token_budget
- Added semantic_score_threshold config
- Fixed streaming response handling
- Python-based healthcheck (no curl dependency)

app/singleton.py

@@ -0,0 +1,19 @@
+"""Global singleton instances for Vera-AI."""
+from .qdrant_service import QdrantService
+from .config import config
+
+_qdrant_service: QdrantService = None
+
+
+def get_qdrant_service() -> QdrantService:
+    """Get or create the global QdrantService singleton."""
+    global _qdrant_service
+    if _qdrant_service is None:
+        _qdrant_service = QdrantService(
+            host=config.qdrant_host,
+            collection=config.qdrant_collection,
+            embedding_model=config.embedding_model,
+            vector_size=config.vector_size,
+            ollama_host=config.ollama_host
+        )
+    return _qdrant_service