refactor: worker mode — server offloads all LLM/exec to worker

- Split into `tori server` / `tori worker` subcommands (clap derive)
- Extract lib.rs for shared crate (agent, llm, exec, state, etc.)
- Introduce AgentUpdate channel to decouple agent loop from DB/broadcast
- New sink.rs: AgentUpdate enum + ServiceManager + handle_agent_updates
- New worker_runner.rs: connects to server WS, runs full agent loop
- Expand worker protocol: ServerToWorker (workflow_assign, comment)
  and WorkerToServer (register, result, update)
- Remove LLM from title generation (heuristic) and template selection
  (must be explicit)
- Remove KB tools (kb_search, kb_read) and remote worker tools
  (list_workers, execute_on_worker) from agent loop
- run_agent_loop/run_step_loop now take mpsc::Sender<AgentUpdate>
  instead of direct DB pool + broadcast sender

Cargo.toml

@@ -19,11 +19,14 @@ sqlx = { version = "0.8", features = ["runtime-tokio", "sqlite"] }
 tower-http = { version = "0.6", features = ["cors", "fs"] }
 reqwest = { version = "0.12", default-features = false, features = ["json", "stream", "rustls-tls"] }
 futures = "0.3"
+tokio-tungstenite = { version = "0.26", features = ["rustls-tls-webpki-roots"] }
 tracing = "0.1"
 tracing-subscriber = { version = "0.3", features = ["env-filter"] }
 chrono = { version = "0.4", features = ["serde"] }
 uuid = { version = "1", features = ["v4"] }
 anyhow = "1"
+clap = { version = "4", features = ["derive", "env"] }
+hostname = "0.4"
 mime_guess = "2"
 tokio-util = { version = "0.7", features = ["io"] }
 nix = { version = "0.29", features = ["signal"] }