recv: optional wait_seconds parameter, capped at 60s

AgentRequest::Recv and ManagerRequest::Recv grow an optional
wait_seconds field (default None → 30s, capped at 60s server-side).
agent_server / manager_server clamp via recv_timeout(). MCP tool
schemas advertise the param so claude can pick its own poll window
— useful when an agent wants to throttle wakes without entering a
distinct nap state.

both harness loops still pass None, keeping the existing 30s
default behaviour for system-level Recvs.

hive-ag3nt/src/bin/hive-ag3nt.rs

@@ -116,7 +116,8 @@ async fn serve(
     let label = std::env::var("HIVE_LABEL").unwrap_or_else(|_| "hive-ag3nt".into());
     let system_prompt = turn::write_system_prompt(socket, &label, mcp::Flavor::Agent).await?;
     loop {
-        let recv: Result<AgentResponse> = client::request(socket, &AgentRequest::Recv).await;
+        let recv: Result<AgentResponse> =
+            client::request(socket, &AgentRequest::Recv { wait_seconds: None }).await;
         match recv {
             Ok(AgentResponse::Message { from, body }) => {
                 tracing::info!(%from, %body, "inbox");