feat: implement full pipeline (pgvector, embeddings, ingest, query, HTTP)

- Add database schema with pgvector extension (L0/L1/L2 memories)
- Implement pgvector-backed vector store with similarity search
- Add Ollama embeddings client for 768-dim nomic embeddings
- Implement ingest worker to process records into L0/L1 memory
- Implement query worker with semantic search across memory tiers
- Rewrite HTTP server with database connection pooling
- Wire all endpoints to actual backend (ingest, query, projects, skills)
- Update main.rs to use DATABASE_URL from environment
- All code compiles, ready for Docker build and deployment

crates/mem-llm/src/lib.rs

@@ -1,5 +1,7 @@
 pub mod chat;
 pub mod rerank;
+pub mod embeddings;
 
 pub use chat::{ChatClient, Completion, Usage};
 pub use rerank::RerankClient;
+pub use embeddings::EmbeddingsClient;