Revert to tokio::sync::Mutex, fix lock-across-await bugs, move input ownership to InteractScreen

The std::sync::Mutex detour caught every place a MutexGuard lived
across an await point in Agent::turn — the compiler enforced Send
safety that tokio::sync::Mutex silently allows. With those fixed,
switch back to tokio::sync::Mutex (std::sync blocks tokio worker
threads and panics inside the runtime).

Input and command dispatch now live in InteractScreen (chat.rs):
- Enter pushes directly to SharedMindState.input (no app.submitted hop)
- sync_from_agent displays pending input with dimmed color
- Slash command table moved from event_loop.rs to chat.rs
- cmd_switch_model kept as pub fn for tool-initiated switches

Co-Authored-By: Proof of Concept <poc@bcachefs.org>

src/agent/tools/working_stack.rs

@@ -20,7 +20,7 @@ pub fn tool() -> super::Tool {
         parameters_json: r#"{"type":"object","properties":{"action":{"type":"string","enum":["push","pop","update","switch"],"description":"Stack operation"},"content":{"type":"string","description":"Task description (for push/update)"},"index":{"type":"integer","description":"Stack index (for switch, 0=bottom)"}},"required":["action"]}"#,
         handler: |agent, v| Box::pin(async move {
             if let Some(agent) = agent {
-                let mut a = agent.lock().unwrap();
+                let mut a = agent.lock().await;
                 Ok(handle(&v, &mut a.context.working_stack))
             } else {
                 anyhow::bail!("working_stack requires agent context")