add OpenAI-compatible backend, markdown rendering, and sendMessageDraft fix

- Configurable backend: claude (CLI) or openai (API), selected in config.yaml
- OpenAI streaming via SSE with conversation history in memory
- Session isolation: config name included in session UUID
- Markdown to Telegram HTML conversion (pulldown-cmark) for final messages
- Fix sendMessageDraft: skip cursor to preserve monotonic text growth,
  skip empty content chunks from SSE stream
- Simplify Makefile: single deploy target

Cargo.toml

@@ -10,6 +10,7 @@ dptree = "0.3"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
 serde_yaml = "0.9"
+pulldown-cmark = "0.12"
 reqwest = { version = "0.12", features = ["json"] }
 teloxide = { version = "0.12", features = ["macros"] }
 tokio = { version = "1", features = ["full"] }